Deep Multicameral Decoding for Localizing Unoccluded Object Instances from a Single RGB Image
Abstract Occlusion-aware instance-sensitive segmentation is a complex task generally split into region-based segmentations, by approximating instances as their bounding box. We address the showcase scenario of dense homogeneous layouts in which this approximation does not hold. In this scenario, out...
Ausführliche Beschreibung
Autor*in: |
Grard, Matthieu [verfasserIn] |
---|
Format: |
Artikel |
---|---|
Sprache: |
Englisch |
Erschienen: |
2020 |
---|
Schlagwörter: |
Instance boundary and occlusion detection |
---|
Anmerkung: |
© Springer Science+Business Media, LLC, part of Springer Nature 2020 |
---|
Übergeordnetes Werk: |
Enthalten in: International journal of computer vision - Springer US, 1987, 128(2020), 5 vom: 27. März, Seite 1331-1359 |
---|---|
Übergeordnetes Werk: |
volume:128 ; year:2020 ; number:5 ; day:27 ; month:03 ; pages:1331-1359 |
Links: |
---|
DOI / URN: |
10.1007/s11263-020-01323-0 |
---|
Katalog-ID: |
OLC2057754049 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | OLC2057754049 | ||
003 | DE-627 | ||
005 | 20230504135654.0 | ||
007 | tu | ||
008 | 200819s2020 xx ||||| 00| ||eng c | ||
024 | 7 | |a 10.1007/s11263-020-01323-0 |2 doi | |
035 | |a (DE-627)OLC2057754049 | ||
035 | |a (DE-He213)s11263-020-01323-0-p | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
082 | 0 | 4 | |a 004 |q VZ |
100 | 1 | |a Grard, Matthieu |e verfasserin |4 aut | |
245 | 1 | 0 | |a Deep Multicameral Decoding for Localizing Unoccluded Object Instances from a Single RGB Image |
264 | 1 | |c 2020 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ohne Hilfsmittel zu benutzen |b n |2 rdamedia | ||
338 | |a Band |b nc |2 rdacarrier | ||
500 | |a © Springer Science+Business Media, LLC, part of Springer Nature 2020 | ||
520 | |a Abstract Occlusion-aware instance-sensitive segmentation is a complex task generally split into region-based segmentations, by approximating instances as their bounding box. We address the showcase scenario of dense homogeneous layouts in which this approximation does not hold. In this scenario, outlining unoccluded instances by decoding a deep encoder becomes difficult, due to the translation invariance of convolutional layers and the lack of complexity in the decoder. We therefore propose a multicameral design composed of subtask-specific lightweight decoder and encoder–decoder units, coupled in cascade to encourage subtask-specific feature reuse and enforce a learning path within the decoding process. Furthermore, the state-of-the-art datasets for occlusion-aware instance segmentation contain real images with few instances and occlusions mostly due to objects occluding the background, unlike dense object layouts. We thus also introduce a synthetic dataset of dense homogeneous object layouts, namely Mikado, which extensibly contains more instances and inter-instance occlusions per image than these public datasets. Our extensive experiments on Mikado and public datasets show that ordinal multiscale units within the decoding process prove more effective than state-of-the-art design patterns for capturing position-sensitive representations. We also show that Mikado is plausible with respect to real-world problems, in the sense that it enables the learning of performance-enhancing representations transferable to real images, while drastically reducing the need of hand-made annotations for finetuning. The proposed dataset will be made publicly available. | ||
650 | 4 | |a Instance boundary and occlusion detection | |
650 | 4 | |a Fully convolutional encoder–decoder networks | |
650 | 4 | |a Synthetic data | |
650 | 4 | |a Domain adaptation | |
700 | 1 | |a Dellandréa, Emmanuel |4 aut | |
700 | 1 | |a Chen, Liming |4 aut | |
773 | 0 | 8 | |i Enthalten in |t International journal of computer vision |d Springer US, 1987 |g 128(2020), 5 vom: 27. März, Seite 1331-1359 |w (DE-627)129354252 |w (DE-600)155895-X |w (DE-576)018081428 |x 0920-5691 |7 nnns |
773 | 1 | 8 | |g volume:128 |g year:2020 |g number:5 |g day:27 |g month:03 |g pages:1331-1359 |
856 | 4 | 1 | |u https://doi.org/10.1007/s11263-020-01323-0 |z lizenzpflichtig |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a SYSFLAG_A | ||
912 | |a GBV_OLC | ||
912 | |a SSG-OLC-MAT | ||
912 | |a GBV_ILN_2244 | ||
951 | |a AR | ||
952 | |d 128 |j 2020 |e 5 |b 27 |c 03 |h 1331-1359 |
author_variant |
m g mg e d ed l c lc |
---|---|
matchkey_str |
article:09205691:2020----::eputcmrleoigolclznuocueojcisac |
hierarchy_sort_str |
2020 |
publishDate |
2020 |
allfields |
10.1007/s11263-020-01323-0 doi (DE-627)OLC2057754049 (DE-He213)s11263-020-01323-0-p DE-627 ger DE-627 rakwb eng 004 VZ Grard, Matthieu verfasserin aut Deep Multicameral Decoding for Localizing Unoccluded Object Instances from a Single RGB Image 2020 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © Springer Science+Business Media, LLC, part of Springer Nature 2020 Abstract Occlusion-aware instance-sensitive segmentation is a complex task generally split into region-based segmentations, by approximating instances as their bounding box. We address the showcase scenario of dense homogeneous layouts in which this approximation does not hold. In this scenario, outlining unoccluded instances by decoding a deep encoder becomes difficult, due to the translation invariance of convolutional layers and the lack of complexity in the decoder. We therefore propose a multicameral design composed of subtask-specific lightweight decoder and encoder–decoder units, coupled in cascade to encourage subtask-specific feature reuse and enforce a learning path within the decoding process. Furthermore, the state-of-the-art datasets for occlusion-aware instance segmentation contain real images with few instances and occlusions mostly due to objects occluding the background, unlike dense object layouts. We thus also introduce a synthetic dataset of dense homogeneous object layouts, namely Mikado, which extensibly contains more instances and inter-instance occlusions per image than these public datasets. Our extensive experiments on Mikado and public datasets show that ordinal multiscale units within the decoding process prove more effective than state-of-the-art design patterns for capturing position-sensitive representations. We also show that Mikado is plausible with respect to real-world problems, in the sense that it enables the learning of performance-enhancing representations transferable to real images, while drastically reducing the need of hand-made annotations for finetuning. The proposed dataset will be made publicly available. Instance boundary and occlusion detection Fully convolutional encoder–decoder networks Synthetic data Domain adaptation Dellandréa, Emmanuel aut Chen, Liming aut Enthalten in International journal of computer vision Springer US, 1987 128(2020), 5 vom: 27. März, Seite 1331-1359 (DE-627)129354252 (DE-600)155895-X (DE-576)018081428 0920-5691 nnns volume:128 year:2020 number:5 day:27 month:03 pages:1331-1359 https://doi.org/10.1007/s11263-020-01323-0 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_2244 AR 128 2020 5 27 03 1331-1359 |
spelling |
10.1007/s11263-020-01323-0 doi (DE-627)OLC2057754049 (DE-He213)s11263-020-01323-0-p DE-627 ger DE-627 rakwb eng 004 VZ Grard, Matthieu verfasserin aut Deep Multicameral Decoding for Localizing Unoccluded Object Instances from a Single RGB Image 2020 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © Springer Science+Business Media, LLC, part of Springer Nature 2020 Abstract Occlusion-aware instance-sensitive segmentation is a complex task generally split into region-based segmentations, by approximating instances as their bounding box. We address the showcase scenario of dense homogeneous layouts in which this approximation does not hold. In this scenario, outlining unoccluded instances by decoding a deep encoder becomes difficult, due to the translation invariance of convolutional layers and the lack of complexity in the decoder. We therefore propose a multicameral design composed of subtask-specific lightweight decoder and encoder–decoder units, coupled in cascade to encourage subtask-specific feature reuse and enforce a learning path within the decoding process. Furthermore, the state-of-the-art datasets for occlusion-aware instance segmentation contain real images with few instances and occlusions mostly due to objects occluding the background, unlike dense object layouts. We thus also introduce a synthetic dataset of dense homogeneous object layouts, namely Mikado, which extensibly contains more instances and inter-instance occlusions per image than these public datasets. Our extensive experiments on Mikado and public datasets show that ordinal multiscale units within the decoding process prove more effective than state-of-the-art design patterns for capturing position-sensitive representations. We also show that Mikado is plausible with respect to real-world problems, in the sense that it enables the learning of performance-enhancing representations transferable to real images, while drastically reducing the need of hand-made annotations for finetuning. The proposed dataset will be made publicly available. Instance boundary and occlusion detection Fully convolutional encoder–decoder networks Synthetic data Domain adaptation Dellandréa, Emmanuel aut Chen, Liming aut Enthalten in International journal of computer vision Springer US, 1987 128(2020), 5 vom: 27. März, Seite 1331-1359 (DE-627)129354252 (DE-600)155895-X (DE-576)018081428 0920-5691 nnns volume:128 year:2020 number:5 day:27 month:03 pages:1331-1359 https://doi.org/10.1007/s11263-020-01323-0 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_2244 AR 128 2020 5 27 03 1331-1359 |
allfields_unstemmed |
10.1007/s11263-020-01323-0 doi (DE-627)OLC2057754049 (DE-He213)s11263-020-01323-0-p DE-627 ger DE-627 rakwb eng 004 VZ Grard, Matthieu verfasserin aut Deep Multicameral Decoding for Localizing Unoccluded Object Instances from a Single RGB Image 2020 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © Springer Science+Business Media, LLC, part of Springer Nature 2020 Abstract Occlusion-aware instance-sensitive segmentation is a complex task generally split into region-based segmentations, by approximating instances as their bounding box. We address the showcase scenario of dense homogeneous layouts in which this approximation does not hold. In this scenario, outlining unoccluded instances by decoding a deep encoder becomes difficult, due to the translation invariance of convolutional layers and the lack of complexity in the decoder. We therefore propose a multicameral design composed of subtask-specific lightweight decoder and encoder–decoder units, coupled in cascade to encourage subtask-specific feature reuse and enforce a learning path within the decoding process. Furthermore, the state-of-the-art datasets for occlusion-aware instance segmentation contain real images with few instances and occlusions mostly due to objects occluding the background, unlike dense object layouts. We thus also introduce a synthetic dataset of dense homogeneous object layouts, namely Mikado, which extensibly contains more instances and inter-instance occlusions per image than these public datasets. Our extensive experiments on Mikado and public datasets show that ordinal multiscale units within the decoding process prove more effective than state-of-the-art design patterns for capturing position-sensitive representations. We also show that Mikado is plausible with respect to real-world problems, in the sense that it enables the learning of performance-enhancing representations transferable to real images, while drastically reducing the need of hand-made annotations for finetuning. The proposed dataset will be made publicly available. Instance boundary and occlusion detection Fully convolutional encoder–decoder networks Synthetic data Domain adaptation Dellandréa, Emmanuel aut Chen, Liming aut Enthalten in International journal of computer vision Springer US, 1987 128(2020), 5 vom: 27. März, Seite 1331-1359 (DE-627)129354252 (DE-600)155895-X (DE-576)018081428 0920-5691 nnns volume:128 year:2020 number:5 day:27 month:03 pages:1331-1359 https://doi.org/10.1007/s11263-020-01323-0 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_2244 AR 128 2020 5 27 03 1331-1359 |
allfieldsGer |
10.1007/s11263-020-01323-0 doi (DE-627)OLC2057754049 (DE-He213)s11263-020-01323-0-p DE-627 ger DE-627 rakwb eng 004 VZ Grard, Matthieu verfasserin aut Deep Multicameral Decoding for Localizing Unoccluded Object Instances from a Single RGB Image 2020 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © Springer Science+Business Media, LLC, part of Springer Nature 2020 Abstract Occlusion-aware instance-sensitive segmentation is a complex task generally split into region-based segmentations, by approximating instances as their bounding box. We address the showcase scenario of dense homogeneous layouts in which this approximation does not hold. In this scenario, outlining unoccluded instances by decoding a deep encoder becomes difficult, due to the translation invariance of convolutional layers and the lack of complexity in the decoder. We therefore propose a multicameral design composed of subtask-specific lightweight decoder and encoder–decoder units, coupled in cascade to encourage subtask-specific feature reuse and enforce a learning path within the decoding process. Furthermore, the state-of-the-art datasets for occlusion-aware instance segmentation contain real images with few instances and occlusions mostly due to objects occluding the background, unlike dense object layouts. We thus also introduce a synthetic dataset of dense homogeneous object layouts, namely Mikado, which extensibly contains more instances and inter-instance occlusions per image than these public datasets. Our extensive experiments on Mikado and public datasets show that ordinal multiscale units within the decoding process prove more effective than state-of-the-art design patterns for capturing position-sensitive representations. We also show that Mikado is plausible with respect to real-world problems, in the sense that it enables the learning of performance-enhancing representations transferable to real images, while drastically reducing the need of hand-made annotations for finetuning. The proposed dataset will be made publicly available. Instance boundary and occlusion detection Fully convolutional encoder–decoder networks Synthetic data Domain adaptation Dellandréa, Emmanuel aut Chen, Liming aut Enthalten in International journal of computer vision Springer US, 1987 128(2020), 5 vom: 27. März, Seite 1331-1359 (DE-627)129354252 (DE-600)155895-X (DE-576)018081428 0920-5691 nnns volume:128 year:2020 number:5 day:27 month:03 pages:1331-1359 https://doi.org/10.1007/s11263-020-01323-0 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_2244 AR 128 2020 5 27 03 1331-1359 |
allfieldsSound |
10.1007/s11263-020-01323-0 doi (DE-627)OLC2057754049 (DE-He213)s11263-020-01323-0-p DE-627 ger DE-627 rakwb eng 004 VZ Grard, Matthieu verfasserin aut Deep Multicameral Decoding for Localizing Unoccluded Object Instances from a Single RGB Image 2020 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier © Springer Science+Business Media, LLC, part of Springer Nature 2020 Abstract Occlusion-aware instance-sensitive segmentation is a complex task generally split into region-based segmentations, by approximating instances as their bounding box. We address the showcase scenario of dense homogeneous layouts in which this approximation does not hold. In this scenario, outlining unoccluded instances by decoding a deep encoder becomes difficult, due to the translation invariance of convolutional layers and the lack of complexity in the decoder. We therefore propose a multicameral design composed of subtask-specific lightweight decoder and encoder–decoder units, coupled in cascade to encourage subtask-specific feature reuse and enforce a learning path within the decoding process. Furthermore, the state-of-the-art datasets for occlusion-aware instance segmentation contain real images with few instances and occlusions mostly due to objects occluding the background, unlike dense object layouts. We thus also introduce a synthetic dataset of dense homogeneous object layouts, namely Mikado, which extensibly contains more instances and inter-instance occlusions per image than these public datasets. Our extensive experiments on Mikado and public datasets show that ordinal multiscale units within the decoding process prove more effective than state-of-the-art design patterns for capturing position-sensitive representations. We also show that Mikado is plausible with respect to real-world problems, in the sense that it enables the learning of performance-enhancing representations transferable to real images, while drastically reducing the need of hand-made annotations for finetuning. The proposed dataset will be made publicly available. Instance boundary and occlusion detection Fully convolutional encoder–decoder networks Synthetic data Domain adaptation Dellandréa, Emmanuel aut Chen, Liming aut Enthalten in International journal of computer vision Springer US, 1987 128(2020), 5 vom: 27. März, Seite 1331-1359 (DE-627)129354252 (DE-600)155895-X (DE-576)018081428 0920-5691 nnns volume:128 year:2020 number:5 day:27 month:03 pages:1331-1359 https://doi.org/10.1007/s11263-020-01323-0 lizenzpflichtig Volltext GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_2244 AR 128 2020 5 27 03 1331-1359 |
language |
English |
source |
Enthalten in International journal of computer vision 128(2020), 5 vom: 27. März, Seite 1331-1359 volume:128 year:2020 number:5 day:27 month:03 pages:1331-1359 |
sourceStr |
Enthalten in International journal of computer vision 128(2020), 5 vom: 27. März, Seite 1331-1359 volume:128 year:2020 number:5 day:27 month:03 pages:1331-1359 |
format_phy_str_mv |
Article |
institution |
findex.gbv.de |
topic_facet |
Instance boundary and occlusion detection Fully convolutional encoder–decoder networks Synthetic data Domain adaptation |
dewey-raw |
004 |
isfreeaccess_bool |
false |
container_title |
International journal of computer vision |
authorswithroles_txt_mv |
Grard, Matthieu @@aut@@ Dellandréa, Emmanuel @@aut@@ Chen, Liming @@aut@@ |
publishDateDaySort_date |
2020-03-27T00:00:00Z |
hierarchy_top_id |
129354252 |
dewey-sort |
14 |
id |
OLC2057754049 |
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">OLC2057754049</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230504135654.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">200819s2020 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s11263-020-01323-0</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC2057754049</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s11263-020-01323-0-p</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">rakwb</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">VZ</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Grard, Matthieu</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Deep Multicameral Decoding for Localizing Unoccluded Object Instances from a Single RGB Image</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2020</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">ohne Hilfsmittel zu benutzen</subfield><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Band</subfield><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">© Springer Science+Business Media, LLC, part of Springer Nature 2020</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract Occlusion-aware instance-sensitive segmentation is a complex task generally split into region-based segmentations, by approximating instances as their bounding box. We address the showcase scenario of dense homogeneous layouts in which this approximation does not hold. In this scenario, outlining unoccluded instances by decoding a deep encoder becomes difficult, due to the translation invariance of convolutional layers and the lack of complexity in the decoder. We therefore propose a multicameral design composed of subtask-specific lightweight decoder and encoder–decoder units, coupled in cascade to encourage subtask-specific feature reuse and enforce a learning path within the decoding process. Furthermore, the state-of-the-art datasets for occlusion-aware instance segmentation contain real images with few instances and occlusions mostly due to objects occluding the background, unlike dense object layouts. We thus also introduce a synthetic dataset of dense homogeneous object layouts, namely Mikado, which extensibly contains more instances and inter-instance occlusions per image than these public datasets. Our extensive experiments on Mikado and public datasets show that ordinal multiscale units within the decoding process prove more effective than state-of-the-art design patterns for capturing position-sensitive representations. We also show that Mikado is plausible with respect to real-world problems, in the sense that it enables the learning of performance-enhancing representations transferable to real images, while drastically reducing the need of hand-made annotations for finetuning. The proposed dataset will be made publicly available.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Instance boundary and occlusion detection</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Fully convolutional encoder–decoder networks</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Synthetic data</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Domain adaptation</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Dellandréa, Emmanuel</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Chen, Liming</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">International journal of computer vision</subfield><subfield code="d">Springer US, 1987</subfield><subfield code="g">128(2020), 5 vom: 27. März, Seite 1331-1359</subfield><subfield code="w">(DE-627)129354252</subfield><subfield code="w">(DE-600)155895-X</subfield><subfield code="w">(DE-576)018081428</subfield><subfield code="x">0920-5691</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:128</subfield><subfield code="g">year:2020</subfield><subfield code="g">number:5</subfield><subfield code="g">day:27</subfield><subfield code="g">month:03</subfield><subfield code="g">pages:1331-1359</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s11263-020-01323-0</subfield><subfield code="z">lizenzpflichtig</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_OLC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-MAT</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2244</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">128</subfield><subfield code="j">2020</subfield><subfield code="e">5</subfield><subfield code="b">27</subfield><subfield code="c">03</subfield><subfield code="h">1331-1359</subfield></datafield></record></collection>
|
author |
Grard, Matthieu |
spellingShingle |
Grard, Matthieu ddc 004 misc Instance boundary and occlusion detection misc Fully convolutional encoder–decoder networks misc Synthetic data misc Domain adaptation Deep Multicameral Decoding for Localizing Unoccluded Object Instances from a Single RGB Image |
authorStr |
Grard, Matthieu |
ppnlink_with_tag_str_mv |
@@773@@(DE-627)129354252 |
format |
Article |
dewey-ones |
004 - Data processing & computer science |
delete_txt_mv |
keep |
author_role |
aut aut aut |
collection |
OLC |
remote_str |
false |
illustrated |
Not Illustrated |
issn |
0920-5691 |
topic_title |
004 VZ Deep Multicameral Decoding for Localizing Unoccluded Object Instances from a Single RGB Image Instance boundary and occlusion detection Fully convolutional encoder–decoder networks Synthetic data Domain adaptation |
topic |
ddc 004 misc Instance boundary and occlusion detection misc Fully convolutional encoder–decoder networks misc Synthetic data misc Domain adaptation |
topic_unstemmed |
ddc 004 misc Instance boundary and occlusion detection misc Fully convolutional encoder–decoder networks misc Synthetic data misc Domain adaptation |
topic_browse |
ddc 004 misc Instance boundary and occlusion detection misc Fully convolutional encoder–decoder networks misc Synthetic data misc Domain adaptation |
format_facet |
Aufsätze Gedruckte Aufsätze |
format_main_str_mv |
Text Zeitschrift/Artikel |
carriertype_str_mv |
nc |
hierarchy_parent_title |
International journal of computer vision |
hierarchy_parent_id |
129354252 |
dewey-tens |
000 - Computer science, knowledge & systems |
hierarchy_top_title |
International journal of computer vision |
isfreeaccess_txt |
false |
familylinks_str_mv |
(DE-627)129354252 (DE-600)155895-X (DE-576)018081428 |
title |
Deep Multicameral Decoding for Localizing Unoccluded Object Instances from a Single RGB Image |
ctrlnum |
(DE-627)OLC2057754049 (DE-He213)s11263-020-01323-0-p |
title_full |
Deep Multicameral Decoding for Localizing Unoccluded Object Instances from a Single RGB Image |
author_sort |
Grard, Matthieu |
journal |
International journal of computer vision |
journalStr |
International journal of computer vision |
lang_code |
eng |
isOA_bool |
false |
dewey-hundreds |
000 - Computer science, information & general works |
recordtype |
marc |
publishDateSort |
2020 |
contenttype_str_mv |
txt |
container_start_page |
1331 |
author_browse |
Grard, Matthieu Dellandréa, Emmanuel Chen, Liming |
container_volume |
128 |
class |
004 VZ |
format_se |
Aufsätze |
author-letter |
Grard, Matthieu |
doi_str_mv |
10.1007/s11263-020-01323-0 |
dewey-full |
004 |
title_sort |
deep multicameral decoding for localizing unoccluded object instances from a single rgb image |
title_auth |
Deep Multicameral Decoding for Localizing Unoccluded Object Instances from a Single RGB Image |
abstract |
Abstract Occlusion-aware instance-sensitive segmentation is a complex task generally split into region-based segmentations, by approximating instances as their bounding box. We address the showcase scenario of dense homogeneous layouts in which this approximation does not hold. In this scenario, outlining unoccluded instances by decoding a deep encoder becomes difficult, due to the translation invariance of convolutional layers and the lack of complexity in the decoder. We therefore propose a multicameral design composed of subtask-specific lightweight decoder and encoder–decoder units, coupled in cascade to encourage subtask-specific feature reuse and enforce a learning path within the decoding process. Furthermore, the state-of-the-art datasets for occlusion-aware instance segmentation contain real images with few instances and occlusions mostly due to objects occluding the background, unlike dense object layouts. We thus also introduce a synthetic dataset of dense homogeneous object layouts, namely Mikado, which extensibly contains more instances and inter-instance occlusions per image than these public datasets. Our extensive experiments on Mikado and public datasets show that ordinal multiscale units within the decoding process prove more effective than state-of-the-art design patterns for capturing position-sensitive representations. We also show that Mikado is plausible with respect to real-world problems, in the sense that it enables the learning of performance-enhancing representations transferable to real images, while drastically reducing the need of hand-made annotations for finetuning. The proposed dataset will be made publicly available. © Springer Science+Business Media, LLC, part of Springer Nature 2020 |
abstractGer |
Abstract Occlusion-aware instance-sensitive segmentation is a complex task generally split into region-based segmentations, by approximating instances as their bounding box. We address the showcase scenario of dense homogeneous layouts in which this approximation does not hold. In this scenario, outlining unoccluded instances by decoding a deep encoder becomes difficult, due to the translation invariance of convolutional layers and the lack of complexity in the decoder. We therefore propose a multicameral design composed of subtask-specific lightweight decoder and encoder–decoder units, coupled in cascade to encourage subtask-specific feature reuse and enforce a learning path within the decoding process. Furthermore, the state-of-the-art datasets for occlusion-aware instance segmentation contain real images with few instances and occlusions mostly due to objects occluding the background, unlike dense object layouts. We thus also introduce a synthetic dataset of dense homogeneous object layouts, namely Mikado, which extensibly contains more instances and inter-instance occlusions per image than these public datasets. Our extensive experiments on Mikado and public datasets show that ordinal multiscale units within the decoding process prove more effective than state-of-the-art design patterns for capturing position-sensitive representations. We also show that Mikado is plausible with respect to real-world problems, in the sense that it enables the learning of performance-enhancing representations transferable to real images, while drastically reducing the need of hand-made annotations for finetuning. The proposed dataset will be made publicly available. © Springer Science+Business Media, LLC, part of Springer Nature 2020 |
abstract_unstemmed |
Abstract Occlusion-aware instance-sensitive segmentation is a complex task generally split into region-based segmentations, by approximating instances as their bounding box. We address the showcase scenario of dense homogeneous layouts in which this approximation does not hold. In this scenario, outlining unoccluded instances by decoding a deep encoder becomes difficult, due to the translation invariance of convolutional layers and the lack of complexity in the decoder. We therefore propose a multicameral design composed of subtask-specific lightweight decoder and encoder–decoder units, coupled in cascade to encourage subtask-specific feature reuse and enforce a learning path within the decoding process. Furthermore, the state-of-the-art datasets for occlusion-aware instance segmentation contain real images with few instances and occlusions mostly due to objects occluding the background, unlike dense object layouts. We thus also introduce a synthetic dataset of dense homogeneous object layouts, namely Mikado, which extensibly contains more instances and inter-instance occlusions per image than these public datasets. Our extensive experiments on Mikado and public datasets show that ordinal multiscale units within the decoding process prove more effective than state-of-the-art design patterns for capturing position-sensitive representations. We also show that Mikado is plausible with respect to real-world problems, in the sense that it enables the learning of performance-enhancing representations transferable to real images, while drastically reducing the need of hand-made annotations for finetuning. The proposed dataset will be made publicly available. © Springer Science+Business Media, LLC, part of Springer Nature 2020 |
collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT GBV_ILN_2244 |
container_issue |
5 |
title_short |
Deep Multicameral Decoding for Localizing Unoccluded Object Instances from a Single RGB Image |
url |
https://doi.org/10.1007/s11263-020-01323-0 |
remote_bool |
false |
author2 |
Dellandréa, Emmanuel Chen, Liming |
author2Str |
Dellandréa, Emmanuel Chen, Liming |
ppnlink |
129354252 |
mediatype_str_mv |
n |
isOA_txt |
false |
hochschulschrift_bool |
false |
doi_str |
10.1007/s11263-020-01323-0 |
up_date |
2024-07-03T16:10:40.811Z |
_version_ |
1803574880040386560 |
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">OLC2057754049</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230504135654.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">200819s2020 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1007/s11263-020-01323-0</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC2057754049</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-He213)s11263-020-01323-0-p</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">rakwb</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">VZ</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Grard, Matthieu</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Deep Multicameral Decoding for Localizing Unoccluded Object Instances from a Single RGB Image</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2020</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">ohne Hilfsmittel zu benutzen</subfield><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Band</subfield><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="500" ind1=" " ind2=" "><subfield code="a">© Springer Science+Business Media, LLC, part of Springer Nature 2020</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Abstract Occlusion-aware instance-sensitive segmentation is a complex task generally split into region-based segmentations, by approximating instances as their bounding box. We address the showcase scenario of dense homogeneous layouts in which this approximation does not hold. In this scenario, outlining unoccluded instances by decoding a deep encoder becomes difficult, due to the translation invariance of convolutional layers and the lack of complexity in the decoder. We therefore propose a multicameral design composed of subtask-specific lightweight decoder and encoder–decoder units, coupled in cascade to encourage subtask-specific feature reuse and enforce a learning path within the decoding process. Furthermore, the state-of-the-art datasets for occlusion-aware instance segmentation contain real images with few instances and occlusions mostly due to objects occluding the background, unlike dense object layouts. We thus also introduce a synthetic dataset of dense homogeneous object layouts, namely Mikado, which extensibly contains more instances and inter-instance occlusions per image than these public datasets. Our extensive experiments on Mikado and public datasets show that ordinal multiscale units within the decoding process prove more effective than state-of-the-art design patterns for capturing position-sensitive representations. We also show that Mikado is plausible with respect to real-world problems, in the sense that it enables the learning of performance-enhancing representations transferable to real images, while drastically reducing the need of hand-made annotations for finetuning. The proposed dataset will be made publicly available.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Instance boundary and occlusion detection</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Fully convolutional encoder–decoder networks</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Synthetic data</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">Domain adaptation</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Dellandréa, Emmanuel</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Chen, Liming</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">International journal of computer vision</subfield><subfield code="d">Springer US, 1987</subfield><subfield code="g">128(2020), 5 vom: 27. März, Seite 1331-1359</subfield><subfield code="w">(DE-627)129354252</subfield><subfield code="w">(DE-600)155895-X</subfield><subfield code="w">(DE-576)018081428</subfield><subfield code="x">0920-5691</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:128</subfield><subfield code="g">year:2020</subfield><subfield code="g">number:5</subfield><subfield code="g">day:27</subfield><subfield code="g">month:03</subfield><subfield code="g">pages:1331-1359</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">https://doi.org/10.1007/s11263-020-01323-0</subfield><subfield code="z">lizenzpflichtig</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_OLC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-MAT</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2244</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">128</subfield><subfield code="j">2020</subfield><subfield code="e">5</subfield><subfield code="b">27</subfield><subfield code="c">03</subfield><subfield code="h">1331-1359</subfield></datafield></record></collection>
|
score |
7.399088 |