Regularizing deep networks with label geometry for accurate object localization on small training datasets

Localization is a critical subtask in object detection, which is closely related to spatial information of objects. Most current detectors simply rely on the fitting ability of deep neural networks to regress towards numerical targets such as coordinates of object boxes. Training deep networks for s...
Ausführliche Beschreibung

Gespeichert in:

Autor*in:	Wang, Xiaolian [verfasserIn] Hu, Xiyuan [verfasserIn] Chen, Chen [verfasserIn] Peng, Silong [verfasserIn]

Format:	E-Artikel
Sprache:	Englisch

Erschienen:	2022

Schlagwörter:	Object detection Object localization Label geometry Box evolution Small dataset Human-machine interaction

Übergeordnetes Werk:	Enthalten in: Pattern recognition letters - Amsterdam [u.a.] : Elsevier, 1982, 154, Seite 53-59
Übergeordnetes Werk:	volume:154 ; pages:53-59

DOI / URN:	10.1016/j.patrec.2022.01.004

Katalog-ID:	ELV007419163

Internformat


LEADER	01000caa a22002652 4500
001	ELV007419163
003	DE-627
005	20230524145940.0
007	cr uuu---uuuuu
008	230507s2022 xx \|\|\|\|\|o 00\| \|\|eng c
024	7		\|a 10.1016/j.patrec.2022.01.004 \|2 doi
035			\|a (DE-627)ELV007419163
035			\|a (ELSEVIER)S0167-8655(22)00004-6
040			\|a DE-627 \|b ger \|c DE-627 \|e rda
041			\|a eng
082	0	4	\|a 004 \|q DE-600
084			\|a 54.74 \|2 bkl
100	1		\|a Wang, Xiaolian \|e verfasserin \|4 aut
245	1	0	\|a Regularizing deep networks with label geometry for accurate object localization on small training datasets
264		1	\|c 2022
336			\|a nicht spezifiziert \|b zzz \|2 rdacontent
337			\|a Computermedien \|b c \|2 rdamedia
338			\|a Online-Ressource \|b cr \|2 rdacarrier
520			\|a Localization is a critical subtask in object detection, which is closely related to spatial information of objects. Most current detectors simply rely on the fitting ability of deep neural networks to regress towards numerical targets such as coordinates of object boxes. Training deep networks for sufficient fitting ability requires a large number of annotations that are expensive to obtain. In this work, we fully exploit limited annotations by extracting label geometry to improve localization performance on small datasets. We generate distance transform of bounding box edges according to localization labels, with which we supervise intermediate outputs of networks pixel by pixel to reconstruct object geometry for localization. Distance transform is sensitive to box edges and provides geometric gradients flowing into boundaries. We learn such gradients to enhance geometric-aware features through a coupled training with regression, and use it to refine regressed boxes in an evolutionary manner in inference. Extensive experiments are implemented to demonstrate the effectiveness of our method. Our method can be applied in applications that required human-machine interaction, such as the driver-assistance system in autonomous driving, by providing accurate detections to assist humans in making better decisions.
650		4	\|a Object detection
650		4	\|a Object localization
650		4	\|a Label geometry
650		4	\|a Box evolution
650		4	\|a Small dataset
650		4	\|a Human-machine interaction
700	1		\|a Hu, Xiyuan \|e verfasserin \|4 aut
700	1		\|a Chen, Chen \|e verfasserin \|4 aut
700	1		\|a Peng, Silong \|e verfasserin \|4 aut
773	0	8	\|i Enthalten in \|t Pattern recognition letters \|d Amsterdam [u.a.] : Elsevier, 1982 \|g 154, Seite 53-59 \|h Online-Ressource \|w (DE-627)265784123 \|w (DE-600)1466342-9 \|w (DE-576)074891006 \|x 0167-8655 \|7 nnns
773	1	8	\|g volume:154 \|g pages:53-59
912			\|a GBV_USEFLAG_U
912			\|a SYSFLAG_U
912			\|a GBV_ELV
912			\|a GBV_ILN_20
912			\|a GBV_ILN_22
912			\|a GBV_ILN_23
912			\|a GBV_ILN_24
912			\|a GBV_ILN_31
912			\|a GBV_ILN_32
912			\|a GBV_ILN_40
912			\|a GBV_ILN_60
912			\|a GBV_ILN_62
912			\|a GBV_ILN_63
912			\|a GBV_ILN_65
912			\|a GBV_ILN_69
912			\|a GBV_ILN_70
912			\|a GBV_ILN_73
912			\|a GBV_ILN_74
912			\|a GBV_ILN_90
912			\|a GBV_ILN_95
912			\|a GBV_ILN_100
912			\|a GBV_ILN_101
912			\|a GBV_ILN_105
912			\|a GBV_ILN_110
912			\|a GBV_ILN_150
912			\|a GBV_ILN_151
912			\|a GBV_ILN_224
912			\|a GBV_ILN_370
912			\|a GBV_ILN_602
912			\|a GBV_ILN_702
912			\|a GBV_ILN_2003
912			\|a GBV_ILN_2004
912			\|a GBV_ILN_2005
912			\|a GBV_ILN_2011
912			\|a GBV_ILN_2014
912			\|a GBV_ILN_2015
912			\|a GBV_ILN_2020
912			\|a GBV_ILN_2021
912			\|a GBV_ILN_2025
912			\|a GBV_ILN_2027
912			\|a GBV_ILN_2034
912			\|a GBV_ILN_2038
912			\|a GBV_ILN_2044
912			\|a GBV_ILN_2048
912			\|a GBV_ILN_2049
912			\|a GBV_ILN_2050
912			\|a GBV_ILN_2056
912			\|a GBV_ILN_2059
912			\|a GBV_ILN_2061
912			\|a GBV_ILN_2064
912			\|a GBV_ILN_2065
912			\|a GBV_ILN_2068
912			\|a GBV_ILN_2111
912			\|a GBV_ILN_2112
912			\|a GBV_ILN_2113
912			\|a GBV_ILN_2118
912			\|a GBV_ILN_2122
912			\|a GBV_ILN_2129
912			\|a GBV_ILN_2143
912			\|a GBV_ILN_2147
912			\|a GBV_ILN_2148
912			\|a GBV_ILN_2152
912			\|a GBV_ILN_2153
912			\|a GBV_ILN_2190
912			\|a GBV_ILN_2336
912			\|a GBV_ILN_2507
912			\|a GBV_ILN_2522
912			\|a GBV_ILN_4035
912			\|a GBV_ILN_4037
912			\|a GBV_ILN_4112
912			\|a GBV_ILN_4125
912			\|a GBV_ILN_4126
912			\|a GBV_ILN_4242
912			\|a GBV_ILN_4251
912			\|a GBV_ILN_4305
912			\|a GBV_ILN_4313
912			\|a GBV_ILN_4323
912			\|a GBV_ILN_4324
912			\|a GBV_ILN_4325
912			\|a GBV_ILN_4326
912			\|a GBV_ILN_4333
912			\|a GBV_ILN_4334
912			\|a GBV_ILN_4335
912			\|a GBV_ILN_4338
912			\|a GBV_ILN_4393
936	b	k	\|a 54.74 \|j Maschinelles Sehen
951			\|a AR
952			\|d 154 \|h 53-59

Indexfelder

author_variant	x w xw x h xh c c cc s p sp
matchkey_str	article:01678655:2022----::euaiigepewrsihaegoerfrcuaebetoaiai
hierarchy_sort_str	2022
bklnumber	54.74
publishDate	2022
allfields	10.1016/j.patrec.2022.01.004 doi (DE-627)ELV007419163 (ELSEVIER)S0167-8655(22)00004-6 DE-627 ger DE-627 rda eng 004 DE-600 54.74 bkl Wang, Xiaolian verfasserin aut Regularizing deep networks with label geometry for accurate object localization on small training datasets 2022 nicht spezifiziert zzz rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Localization is a critical subtask in object detection, which is closely related to spatial information of objects. Most current detectors simply rely on the fitting ability of deep neural networks to regress towards numerical targets such as coordinates of object boxes. Training deep networks for sufficient fitting ability requires a large number of annotations that are expensive to obtain. In this work, we fully exploit limited annotations by extracting label geometry to improve localization performance on small datasets. We generate distance transform of bounding box edges according to localization labels, with which we supervise intermediate outputs of networks pixel by pixel to reconstruct object geometry for localization. Distance transform is sensitive to box edges and provides geometric gradients flowing into boundaries. We learn such gradients to enhance geometric-aware features through a coupled training with regression, and use it to refine regressed boxes in an evolutionary manner in inference. Extensive experiments are implemented to demonstrate the effectiveness of our method. Our method can be applied in applications that required human-machine interaction, such as the driver-assistance system in autonomous driving, by providing accurate detections to assist humans in making better decisions. Object detection Object localization Label geometry Box evolution Small dataset Human-machine interaction Hu, Xiyuan verfasserin aut Chen, Chen verfasserin aut Peng, Silong verfasserin aut Enthalten in Pattern recognition letters Amsterdam [u.a.] : Elsevier, 1982 154, Seite 53-59 Online-Ressource (DE-627)265784123 (DE-600)1466342-9 (DE-576)074891006 0167-8655 nnns volume:154 pages:53-59 GBV_USEFLAG_U SYSFLAG_U GBV_ELV GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_150 GBV_ILN_151 GBV_ILN_224 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 GBV_ILN_2003 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2011 GBV_ILN_2014 GBV_ILN_2015 GBV_ILN_2020 GBV_ILN_2021 GBV_ILN_2025 GBV_ILN_2027 GBV_ILN_2034 GBV_ILN_2038 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2049 GBV_ILN_2050 GBV_ILN_2056 GBV_ILN_2059 GBV_ILN_2061 GBV_ILN_2064 GBV_ILN_2065 GBV_ILN_2068 GBV_ILN_2111 GBV_ILN_2112 GBV_ILN_2113 GBV_ILN_2118 GBV_ILN_2122 GBV_ILN_2129 GBV_ILN_2143 GBV_ILN_2147 GBV_ILN_2148 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2190 GBV_ILN_2336 GBV_ILN_2507 GBV_ILN_2522 GBV_ILN_4035 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4242 GBV_ILN_4251 GBV_ILN_4305 GBV_ILN_4313 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4333 GBV_ILN_4334 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4393 54.74 Maschinelles Sehen AR 154 53-59
spelling	10.1016/j.patrec.2022.01.004 doi (DE-627)ELV007419163 (ELSEVIER)S0167-8655(22)00004-6 DE-627 ger DE-627 rda eng 004 DE-600 54.74 bkl Wang, Xiaolian verfasserin aut Regularizing deep networks with label geometry for accurate object localization on small training datasets 2022 nicht spezifiziert zzz rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Localization is a critical subtask in object detection, which is closely related to spatial information of objects. Most current detectors simply rely on the fitting ability of deep neural networks to regress towards numerical targets such as coordinates of object boxes. Training deep networks for sufficient fitting ability requires a large number of annotations that are expensive to obtain. In this work, we fully exploit limited annotations by extracting label geometry to improve localization performance on small datasets. We generate distance transform of bounding box edges according to localization labels, with which we supervise intermediate outputs of networks pixel by pixel to reconstruct object geometry for localization. Distance transform is sensitive to box edges and provides geometric gradients flowing into boundaries. We learn such gradients to enhance geometric-aware features through a coupled training with regression, and use it to refine regressed boxes in an evolutionary manner in inference. Extensive experiments are implemented to demonstrate the effectiveness of our method. Our method can be applied in applications that required human-machine interaction, such as the driver-assistance system in autonomous driving, by providing accurate detections to assist humans in making better decisions. Object detection Object localization Label geometry Box evolution Small dataset Human-machine interaction Hu, Xiyuan verfasserin aut Chen, Chen verfasserin aut Peng, Silong verfasserin aut Enthalten in Pattern recognition letters Amsterdam [u.a.] : Elsevier, 1982 154, Seite 53-59 Online-Ressource (DE-627)265784123 (DE-600)1466342-9 (DE-576)074891006 0167-8655 nnns volume:154 pages:53-59 GBV_USEFLAG_U SYSFLAG_U GBV_ELV GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_150 GBV_ILN_151 GBV_ILN_224 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 GBV_ILN_2003 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2011 GBV_ILN_2014 GBV_ILN_2015 GBV_ILN_2020 GBV_ILN_2021 GBV_ILN_2025 GBV_ILN_2027 GBV_ILN_2034 GBV_ILN_2038 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2049 GBV_ILN_2050 GBV_ILN_2056 GBV_ILN_2059 GBV_ILN_2061 GBV_ILN_2064 GBV_ILN_2065 GBV_ILN_2068 GBV_ILN_2111 GBV_ILN_2112 GBV_ILN_2113 GBV_ILN_2118 GBV_ILN_2122 GBV_ILN_2129 GBV_ILN_2143 GBV_ILN_2147 GBV_ILN_2148 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2190 GBV_ILN_2336 GBV_ILN_2507 GBV_ILN_2522 GBV_ILN_4035 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4242 GBV_ILN_4251 GBV_ILN_4305 GBV_ILN_4313 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4333 GBV_ILN_4334 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4393 54.74 Maschinelles Sehen AR 154 53-59
allfields_unstemmed	10.1016/j.patrec.2022.01.004 doi (DE-627)ELV007419163 (ELSEVIER)S0167-8655(22)00004-6 DE-627 ger DE-627 rda eng 004 DE-600 54.74 bkl Wang, Xiaolian verfasserin aut Regularizing deep networks with label geometry for accurate object localization on small training datasets 2022 nicht spezifiziert zzz rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Localization is a critical subtask in object detection, which is closely related to spatial information of objects. Most current detectors simply rely on the fitting ability of deep neural networks to regress towards numerical targets such as coordinates of object boxes. Training deep networks for sufficient fitting ability requires a large number of annotations that are expensive to obtain. In this work, we fully exploit limited annotations by extracting label geometry to improve localization performance on small datasets. We generate distance transform of bounding box edges according to localization labels, with which we supervise intermediate outputs of networks pixel by pixel to reconstruct object geometry for localization. Distance transform is sensitive to box edges and provides geometric gradients flowing into boundaries. We learn such gradients to enhance geometric-aware features through a coupled training with regression, and use it to refine regressed boxes in an evolutionary manner in inference. Extensive experiments are implemented to demonstrate the effectiveness of our method. Our method can be applied in applications that required human-machine interaction, such as the driver-assistance system in autonomous driving, by providing accurate detections to assist humans in making better decisions. Object detection Object localization Label geometry Box evolution Small dataset Human-machine interaction Hu, Xiyuan verfasserin aut Chen, Chen verfasserin aut Peng, Silong verfasserin aut Enthalten in Pattern recognition letters Amsterdam [u.a.] : Elsevier, 1982 154, Seite 53-59 Online-Ressource (DE-627)265784123 (DE-600)1466342-9 (DE-576)074891006 0167-8655 nnns volume:154 pages:53-59 GBV_USEFLAG_U SYSFLAG_U GBV_ELV GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_150 GBV_ILN_151 GBV_ILN_224 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 GBV_ILN_2003 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2011 GBV_ILN_2014 GBV_ILN_2015 GBV_ILN_2020 GBV_ILN_2021 GBV_ILN_2025 GBV_ILN_2027 GBV_ILN_2034 GBV_ILN_2038 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2049 GBV_ILN_2050 GBV_ILN_2056 GBV_ILN_2059 GBV_ILN_2061 GBV_ILN_2064 GBV_ILN_2065 GBV_ILN_2068 GBV_ILN_2111 GBV_ILN_2112 GBV_ILN_2113 GBV_ILN_2118 GBV_ILN_2122 GBV_ILN_2129 GBV_ILN_2143 GBV_ILN_2147 GBV_ILN_2148 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2190 GBV_ILN_2336 GBV_ILN_2507 GBV_ILN_2522 GBV_ILN_4035 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4242 GBV_ILN_4251 GBV_ILN_4305 GBV_ILN_4313 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4333 GBV_ILN_4334 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4393 54.74 Maschinelles Sehen AR 154 53-59
allfieldsGer	10.1016/j.patrec.2022.01.004 doi (DE-627)ELV007419163 (ELSEVIER)S0167-8655(22)00004-6 DE-627 ger DE-627 rda eng 004 DE-600 54.74 bkl Wang, Xiaolian verfasserin aut Regularizing deep networks with label geometry for accurate object localization on small training datasets 2022 nicht spezifiziert zzz rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Localization is a critical subtask in object detection, which is closely related to spatial information of objects. Most current detectors simply rely on the fitting ability of deep neural networks to regress towards numerical targets such as coordinates of object boxes. Training deep networks for sufficient fitting ability requires a large number of annotations that are expensive to obtain. In this work, we fully exploit limited annotations by extracting label geometry to improve localization performance on small datasets. We generate distance transform of bounding box edges according to localization labels, with which we supervise intermediate outputs of networks pixel by pixel to reconstruct object geometry for localization. Distance transform is sensitive to box edges and provides geometric gradients flowing into boundaries. We learn such gradients to enhance geometric-aware features through a coupled training with regression, and use it to refine regressed boxes in an evolutionary manner in inference. Extensive experiments are implemented to demonstrate the effectiveness of our method. Our method can be applied in applications that required human-machine interaction, such as the driver-assistance system in autonomous driving, by providing accurate detections to assist humans in making better decisions. Object detection Object localization Label geometry Box evolution Small dataset Human-machine interaction Hu, Xiyuan verfasserin aut Chen, Chen verfasserin aut Peng, Silong verfasserin aut Enthalten in Pattern recognition letters Amsterdam [u.a.] : Elsevier, 1982 154, Seite 53-59 Online-Ressource (DE-627)265784123 (DE-600)1466342-9 (DE-576)074891006 0167-8655 nnns volume:154 pages:53-59 GBV_USEFLAG_U SYSFLAG_U GBV_ELV GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_150 GBV_ILN_151 GBV_ILN_224 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 GBV_ILN_2003 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2011 GBV_ILN_2014 GBV_ILN_2015 GBV_ILN_2020 GBV_ILN_2021 GBV_ILN_2025 GBV_ILN_2027 GBV_ILN_2034 GBV_ILN_2038 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2049 GBV_ILN_2050 GBV_ILN_2056 GBV_ILN_2059 GBV_ILN_2061 GBV_ILN_2064 GBV_ILN_2065 GBV_ILN_2068 GBV_ILN_2111 GBV_ILN_2112 GBV_ILN_2113 GBV_ILN_2118 GBV_ILN_2122 GBV_ILN_2129 GBV_ILN_2143 GBV_ILN_2147 GBV_ILN_2148 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2190 GBV_ILN_2336 GBV_ILN_2507 GBV_ILN_2522 GBV_ILN_4035 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4242 GBV_ILN_4251 GBV_ILN_4305 GBV_ILN_4313 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4333 GBV_ILN_4334 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4393 54.74 Maschinelles Sehen AR 154 53-59
allfieldsSound	10.1016/j.patrec.2022.01.004 doi (DE-627)ELV007419163 (ELSEVIER)S0167-8655(22)00004-6 DE-627 ger DE-627 rda eng 004 DE-600 54.74 bkl Wang, Xiaolian verfasserin aut Regularizing deep networks with label geometry for accurate object localization on small training datasets 2022 nicht spezifiziert zzz rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier Localization is a critical subtask in object detection, which is closely related to spatial information of objects. Most current detectors simply rely on the fitting ability of deep neural networks to regress towards numerical targets such as coordinates of object boxes. Training deep networks for sufficient fitting ability requires a large number of annotations that are expensive to obtain. In this work, we fully exploit limited annotations by extracting label geometry to improve localization performance on small datasets. We generate distance transform of bounding box edges according to localization labels, with which we supervise intermediate outputs of networks pixel by pixel to reconstruct object geometry for localization. Distance transform is sensitive to box edges and provides geometric gradients flowing into boundaries. We learn such gradients to enhance geometric-aware features through a coupled training with regression, and use it to refine regressed boxes in an evolutionary manner in inference. Extensive experiments are implemented to demonstrate the effectiveness of our method. Our method can be applied in applications that required human-machine interaction, such as the driver-assistance system in autonomous driving, by providing accurate detections to assist humans in making better decisions. Object detection Object localization Label geometry Box evolution Small dataset Human-machine interaction Hu, Xiyuan verfasserin aut Chen, Chen verfasserin aut Peng, Silong verfasserin aut Enthalten in Pattern recognition letters Amsterdam [u.a.] : Elsevier, 1982 154, Seite 53-59 Online-Ressource (DE-627)265784123 (DE-600)1466342-9 (DE-576)074891006 0167-8655 nnns volume:154 pages:53-59 GBV_USEFLAG_U SYSFLAG_U GBV_ELV GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_150 GBV_ILN_151 GBV_ILN_224 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 GBV_ILN_2003 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2011 GBV_ILN_2014 GBV_ILN_2015 GBV_ILN_2020 GBV_ILN_2021 GBV_ILN_2025 GBV_ILN_2027 GBV_ILN_2034 GBV_ILN_2038 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2049 GBV_ILN_2050 GBV_ILN_2056 GBV_ILN_2059 GBV_ILN_2061 GBV_ILN_2064 GBV_ILN_2065 GBV_ILN_2068 GBV_ILN_2111 GBV_ILN_2112 GBV_ILN_2113 GBV_ILN_2118 GBV_ILN_2122 GBV_ILN_2129 GBV_ILN_2143 GBV_ILN_2147 GBV_ILN_2148 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2190 GBV_ILN_2336 GBV_ILN_2507 GBV_ILN_2522 GBV_ILN_4035 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4242 GBV_ILN_4251 GBV_ILN_4305 GBV_ILN_4313 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4333 GBV_ILN_4334 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4393 54.74 Maschinelles Sehen AR 154 53-59
language	English
source	Enthalten in Pattern recognition letters 154, Seite 53-59 volume:154 pages:53-59
sourceStr	Enthalten in Pattern recognition letters 154, Seite 53-59 volume:154 pages:53-59
format_phy_str_mv	Article
bklname	Maschinelles Sehen
institution	findex.gbv.de
topic_facet	Object detection Object localization Label geometry Box evolution Small dataset Human-machine interaction
dewey-raw	004
isfreeaccess_bool	false
container_title	Pattern recognition letters
authorswithroles_txt_mv	Wang, Xiaolian @@aut@@ Hu, Xiyuan @@aut@@ Chen, Chen @@aut@@ Peng, Silong @@aut@@
publishDateDaySort_date	2022-01-01T00:00:00Z
hierarchy_top_id	265784123
dewey-sort	14
id	ELV007419163
language_de	englisch
fullrecord	<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">ELV007419163</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230524145940.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230507s2022 xx \|\|\|\|\|o 00\| \|\|eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.patrec.2022.01.004</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV007419163</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S0167-8655(22)00004-6</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rda</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">004</subfield><subfield code="q">DE-600</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">54.74</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Wang, Xiaolian</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Regularizing deep networks with label geometry for accurate object localization on small training datasets</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2022</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Localization is a critical subtask in object detection, which is closely related to spatial information of objects. Most current detectors simply rely on the fitting ability of deep neural networks to regress towards numerical targets such as coordinates of object boxes. Training deep networks for sufficient fitting ability requires a large number of annotations that are expensive to obtain. In this work, we fully exploit limited annotations by extracting label geometry to improve localization performance on small datasets. We generate distance transform of bounding box edges according to localization labels, with which we supervise intermediate outputs of networks pixel by pixel to reconstruct object geometry for localization. Distance transform is sensitive to box edges and provides geometric gradients flowing into boundaries. We learn such gradients to enhance geometric-aware features through a coupled training with regression, and use it to refine regressed boxes in an evolutionary manner in inference. Extensive experiments are implemented to demonstrate the effectiveness of our method. Our method can be applied in applications that required human-machine interaction, such as the driver-assistance system in autonomous driving, by providing accurate detections to assist humans in making better decisions.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Object detection</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Object localization</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Label geometry</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Box evolution</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Small dataset</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Human-machine interaction</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Hu, Xiyuan</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Chen, Chen</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Peng, Silong</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Pattern recognition letters</subfield><subfield code="d">Amsterdam [u.a.] : Elsevier, 1982</subfield><subfield code="g">154, Seite 53-59</subfield><subfield code="h">Online-Ressource</subfield><subfield code="w">(DE-627)265784123</subfield><subfield code="w">(DE-600)1466342-9</subfield><subfield code="w">(DE-576)074891006</subfield><subfield code="x">0167-8655</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:154</subfield><subfield code="g">pages:53-59</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_23</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_31</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_32</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_60</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_63</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_74</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_90</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_100</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_101</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_150</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_151</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_224</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_370</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_702</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2003</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2004</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2005</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2011</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2015</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2020</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2021</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2025</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2027</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2034</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2038</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2044</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2048</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2049</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2050</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2056</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2059</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2061</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2064</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2065</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2068</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2111</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2113</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2118</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2122</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2129</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2143</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2147</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2148</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2152</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2153</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2190</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2336</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2507</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2522</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4035</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4125</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4126</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4242</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4251</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4305</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4313</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4323</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4324</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4325</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4326</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4333</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4334</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4335</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4338</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4393</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">54.74</subfield><subfield code="j">Maschinelles Sehen</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">154</subfield><subfield code="h">53-59</subfield></datafield></record></collection>
author	Wang, Xiaolian
spellingShingle	Wang, Xiaolian ddc 004 bkl 54.74 misc Object detection misc Object localization misc Label geometry misc Box evolution misc Small dataset misc Human-machine interaction Regularizing deep networks with label geometry for accurate object localization on small training datasets
authorStr	Wang, Xiaolian
ppnlink_with_tag_str_mv	@@773@@(DE-627)265784123
format	electronic Article
dewey-ones	004 - Data processing & computer science
delete_txt_mv	keep
author_role	aut aut aut aut
collection	elsevier
remote_str	true
illustrated	Not Illustrated
issn	0167-8655
topic_title	004 DE-600 54.74 bkl Regularizing deep networks with label geometry for accurate object localization on small training datasets Object detection Object localization Label geometry Box evolution Small dataset Human-machine interaction
topic	ddc 004 bkl 54.74 misc Object detection misc Object localization misc Label geometry misc Box evolution misc Small dataset misc Human-machine interaction
topic_unstemmed	ddc 004 bkl 54.74 misc Object detection misc Object localization misc Label geometry misc Box evolution misc Small dataset misc Human-machine interaction
topic_browse	ddc 004 bkl 54.74 misc Object detection misc Object localization misc Label geometry misc Box evolution misc Small dataset misc Human-machine interaction
format_facet	Elektronische Aufsätze Aufsätze Elektronische Ressource
format_main_str_mv	Text Zeitschrift/Artikel
carriertype_str_mv	cr
hierarchy_parent_title	Pattern recognition letters
hierarchy_parent_id	265784123
dewey-tens	000 - Computer science, knowledge & systems
hierarchy_top_title	Pattern recognition letters
isfreeaccess_txt	false
familylinks_str_mv	(DE-627)265784123 (DE-600)1466342-9 (DE-576)074891006
title	Regularizing deep networks with label geometry for accurate object localization on small training datasets
ctrlnum	(DE-627)ELV007419163 (ELSEVIER)S0167-8655(22)00004-6
title_full	Regularizing deep networks with label geometry for accurate object localization on small training datasets
author_sort	Wang, Xiaolian
journal	Pattern recognition letters
journalStr	Pattern recognition letters
lang_code	eng
isOA_bool	false
dewey-hundreds	000 - Computer science, information & general works
recordtype	marc
publishDateSort	2022
contenttype_str_mv	zzz
container_start_page	53
author_browse	Wang, Xiaolian Hu, Xiyuan Chen, Chen Peng, Silong
container_volume	154
class	004 DE-600 54.74 bkl
format_se	Elektronische Aufsätze
author-letter	Wang, Xiaolian
doi_str_mv	10.1016/j.patrec.2022.01.004
dewey-full	004
author2-role	verfasserin
title_sort	regularizing deep networks with label geometry for accurate object localization on small training datasets
title_auth	Regularizing deep networks with label geometry for accurate object localization on small training datasets
abstract	Localization is a critical subtask in object detection, which is closely related to spatial information of objects. Most current detectors simply rely on the fitting ability of deep neural networks to regress towards numerical targets such as coordinates of object boxes. Training deep networks for sufficient fitting ability requires a large number of annotations that are expensive to obtain. In this work, we fully exploit limited annotations by extracting label geometry to improve localization performance on small datasets. We generate distance transform of bounding box edges according to localization labels, with which we supervise intermediate outputs of networks pixel by pixel to reconstruct object geometry for localization. Distance transform is sensitive to box edges and provides geometric gradients flowing into boundaries. We learn such gradients to enhance geometric-aware features through a coupled training with regression, and use it to refine regressed boxes in an evolutionary manner in inference. Extensive experiments are implemented to demonstrate the effectiveness of our method. Our method can be applied in applications that required human-machine interaction, such as the driver-assistance system in autonomous driving, by providing accurate detections to assist humans in making better decisions.
abstractGer	Localization is a critical subtask in object detection, which is closely related to spatial information of objects. Most current detectors simply rely on the fitting ability of deep neural networks to regress towards numerical targets such as coordinates of object boxes. Training deep networks for sufficient fitting ability requires a large number of annotations that are expensive to obtain. In this work, we fully exploit limited annotations by extracting label geometry to improve localization performance on small datasets. We generate distance transform of bounding box edges according to localization labels, with which we supervise intermediate outputs of networks pixel by pixel to reconstruct object geometry for localization. Distance transform is sensitive to box edges and provides geometric gradients flowing into boundaries. We learn such gradients to enhance geometric-aware features through a coupled training with regression, and use it to refine regressed boxes in an evolutionary manner in inference. Extensive experiments are implemented to demonstrate the effectiveness of our method. Our method can be applied in applications that required human-machine interaction, such as the driver-assistance system in autonomous driving, by providing accurate detections to assist humans in making better decisions.
abstract_unstemmed	Localization is a critical subtask in object detection, which is closely related to spatial information of objects. Most current detectors simply rely on the fitting ability of deep neural networks to regress towards numerical targets such as coordinates of object boxes. Training deep networks for sufficient fitting ability requires a large number of annotations that are expensive to obtain. In this work, we fully exploit limited annotations by extracting label geometry to improve localization performance on small datasets. We generate distance transform of bounding box edges according to localization labels, with which we supervise intermediate outputs of networks pixel by pixel to reconstruct object geometry for localization. Distance transform is sensitive to box edges and provides geometric gradients flowing into boundaries. We learn such gradients to enhance geometric-aware features through a coupled training with regression, and use it to refine regressed boxes in an evolutionary manner in inference. Extensive experiments are implemented to demonstrate the effectiveness of our method. Our method can be applied in applications that required human-machine interaction, such as the driver-assistance system in autonomous driving, by providing accurate detections to assist humans in making better decisions.
collection_details	GBV_USEFLAG_U SYSFLAG_U GBV_ELV GBV_ILN_20 GBV_ILN_22 GBV_ILN_23 GBV_ILN_24 GBV_ILN_31 GBV_ILN_32 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_74 GBV_ILN_90 GBV_ILN_95 GBV_ILN_100 GBV_ILN_101 GBV_ILN_105 GBV_ILN_110 GBV_ILN_150 GBV_ILN_151 GBV_ILN_224 GBV_ILN_370 GBV_ILN_602 GBV_ILN_702 GBV_ILN_2003 GBV_ILN_2004 GBV_ILN_2005 GBV_ILN_2011 GBV_ILN_2014 GBV_ILN_2015 GBV_ILN_2020 GBV_ILN_2021 GBV_ILN_2025 GBV_ILN_2027 GBV_ILN_2034 GBV_ILN_2038 GBV_ILN_2044 GBV_ILN_2048 GBV_ILN_2049 GBV_ILN_2050 GBV_ILN_2056 GBV_ILN_2059 GBV_ILN_2061 GBV_ILN_2064 GBV_ILN_2065 GBV_ILN_2068 GBV_ILN_2111 GBV_ILN_2112 GBV_ILN_2113 GBV_ILN_2118 GBV_ILN_2122 GBV_ILN_2129 GBV_ILN_2143 GBV_ILN_2147 GBV_ILN_2148 GBV_ILN_2152 GBV_ILN_2153 GBV_ILN_2190 GBV_ILN_2336 GBV_ILN_2507 GBV_ILN_2522 GBV_ILN_4035 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4242 GBV_ILN_4251 GBV_ILN_4305 GBV_ILN_4313 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4326 GBV_ILN_4333 GBV_ILN_4334 GBV_ILN_4335 GBV_ILN_4338 GBV_ILN_4393
title_short	Regularizing deep networks with label geometry for accurate object localization on small training datasets
remote_bool	true
author2	Hu, Xiyuan Chen, Chen Peng, Silong
author2Str	Hu, Xiyuan Chen, Chen Peng, Silong
ppnlink	265784123
mediatype_str_mv	c
isOA_txt	false
hochschulschrift_bool	false
doi_str	10.1016/j.patrec.2022.01.004
up_date	2024-07-07T00:41:02.846Z
_version_	1803878780474753024
fullrecord_marcxml	<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a22002652 4500</leader><controlfield tag="001">ELV007419163</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230524145940.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230507s2022 xx \|\|\|\|\|o 00\| \|\|eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.patrec.2022.01.004</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)ELV007419163</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(ELSEVIER)S0167-8655(22)00004-6</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rda</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">004</subfield><subfield code="q">DE-600</subfield></datafield><datafield tag="084" ind1=" " ind2=" "><subfield code="a">54.74</subfield><subfield code="2">bkl</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Wang, Xiaolian</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Regularizing deep networks with label geometry for accurate object localization on small training datasets</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2022</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">nicht spezifiziert</subfield><subfield code="b">zzz</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Localization is a critical subtask in object detection, which is closely related to spatial information of objects. Most current detectors simply rely on the fitting ability of deep neural networks to regress towards numerical targets such as coordinates of object boxes. Training deep networks for sufficient fitting ability requires a large number of annotations that are expensive to obtain. In this work, we fully exploit limited annotations by extracting label geometry to improve localization performance on small datasets. We generate distance transform of bounding box edges according to localization labels, with which we supervise intermediate outputs of networks pixel by pixel to reconstruct object geometry for localization. Distance transform is sensitive to box edges and provides geometric gradients flowing into boundaries. We learn such gradients to enhance geometric-aware features through a coupled training with regression, and use it to refine regressed boxes in an evolutionary manner in inference. Extensive experiments are implemented to demonstrate the effectiveness of our method. Our method can be applied in applications that required human-machine interaction, such as the driver-assistance system in autonomous driving, by providing accurate detections to assist humans in making better decisions.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Object detection</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Object localization</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Label geometry</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Box evolution</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Small dataset</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Human-machine interaction</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Hu, Xiyuan</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Chen, Chen</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Peng, Silong</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Pattern recognition letters</subfield><subfield code="d">Amsterdam [u.a.] : Elsevier, 1982</subfield><subfield code="g">154, Seite 53-59</subfield><subfield code="h">Online-Ressource</subfield><subfield code="w">(DE-627)265784123</subfield><subfield code="w">(DE-600)1466342-9</subfield><subfield code="w">(DE-576)074891006</subfield><subfield code="x">0167-8655</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:154</subfield><subfield code="g">pages:53-59</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_U</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ELV</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_23</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_31</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_32</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_60</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_63</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_74</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_90</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_100</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_101</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_150</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_151</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_224</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_370</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_702</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2003</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2004</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2005</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2011</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2015</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2020</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2021</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2025</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2027</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2034</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2038</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2044</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2048</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2049</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2050</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2056</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2059</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2061</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2064</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2065</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2068</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2111</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2113</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2118</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2122</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2129</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2143</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2147</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2148</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2152</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2153</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2190</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2336</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2507</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2522</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4035</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4125</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4126</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4242</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4251</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4305</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4313</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4323</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4324</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4325</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4326</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4333</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4334</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4335</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4338</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4393</subfield></datafield><datafield tag="936" ind1="b" ind2="k"><subfield code="a">54.74</subfield><subfield code="j">Maschinelles Sehen</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">154</subfield><subfield code="h">53-59</subfield></datafield></record></collection>
score	7.39812

Nicht das Richtige dabei?

Schreiben Sie uns!

Regularizing deep networks with label geometry for accurate object localization on small training datasets

Nicht das Richtige dabei?

Zugang & Verfügbarkeit

Vorhandene Bände

Nicht das Richtige dabei?