SimT: Handling Open-set Noise for Domain Adaptive Semantic Segmentation
This paper studies a practical domain adaptive (DA) semantic segmentation problem where only pseudo-labeled target data is accessible through a black-box model. Due to the domain gap and label shift between two domains, pseudo-labeled target data contains mixed closed-set and open-set label noises....
Uloženo v:
| Vydáno v: | Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) s. 7022 - 7031 |
|---|---|
| Hlavní autoři: | , , , |
| Médium: | Konferenční příspěvek |
| Jazyk: | angličtina |
| Vydáno: |
IEEE
01.06.2022
|
| Témata: | |
| ISSN: | 1063-6919 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | This paper studies a practical domain adaptive (DA) semantic segmentation problem where only pseudo-labeled target data is accessible through a black-box model. Due to the domain gap and label shift between two domains, pseudo-labeled target data contains mixed closed-set and open-set label noises. In this paper, we propose a simplex noise transition matrix (SimT) to model the mixed noise distributions in DA semantic segmentation and formulate the problem as estimation of SimT. By exploiting computational geometry analysis and properties of segmentation, we design three complementary regularizers, i.e. volume regularization, anchor guidance, convex guarantee, to approximate the true SimT. Specifically, volume regularization minimizes the volume of simplex formed by rows of the non-square SimT, which ensures outputs of segmentation model to fit into the ground truth label distribution. To compensate for the lack of open-set knowledge, anchor guidance and convex guarantee are devised to facilitate the modeling of open-set noise distribution and enhance the discriminative feature learning among closed-set and open-set classes. The estimated SimT is further utilized to correct noise issues in pseudo labels and promote the generalization ability of segmentation model on target domain data. Extensive experimental results demonstrate that the proposed SimT can be flexibly plugged into existing DA methods to boost the performance. The source code is available at https://github.com/CityU-AIM-Group/SimT. |
|---|---|
| AbstractList | This paper studies a practical domain adaptive (DA) semantic segmentation problem where only pseudo-labeled target data is accessible through a black-box model. Due to the domain gap and label shift between two domains, pseudo-labeled target data contains mixed closed-set and open-set label noises. In this paper, we propose a simplex noise transition matrix (SimT) to model the mixed noise distributions in DA semantic segmentation and formulate the problem as estimation of SimT. By exploiting computational geometry analysis and properties of segmentation, we design three complementary regularizers, i.e. volume regularization, anchor guidance, convex guarantee, to approximate the true SimT. Specifically, volume regularization minimizes the volume of simplex formed by rows of the non-square SimT, which ensures outputs of segmentation model to fit into the ground truth label distribution. To compensate for the lack of open-set knowledge, anchor guidance and convex guarantee are devised to facilitate the modeling of open-set noise distribution and enhance the discriminative feature learning among closed-set and open-set classes. The estimated SimT is further utilized to correct noise issues in pseudo labels and promote the generalization ability of segmentation model on target domain data. Extensive experimental results demonstrate that the proposed SimT can be flexibly plugged into existing DA methods to boost the performance. The source code is available at https://github.com/CityU-AIM-Group/SimT. |
| Author | Liu, Jie Liu, Tongliang Yuan, Yixuan Guo, Xiaoqing |
| Author_xml | – sequence: 1 givenname: Xiaoqing surname: Guo fullname: Guo, Xiaoqing email: xqguo.ee@my.cityu.edu.hk organization: City University of Hong Kong – sequence: 2 givenname: Jie surname: Liu fullname: Liu, Jie email: jliu.ee@my.cityu.edu.hk organization: City University of Hong Kong – sequence: 3 givenname: Tongliang surname: Liu fullname: Liu, Tongliang email: tongliang.liu@sydney.edu.au organization: University of Sydney – sequence: 4 givenname: Yixuan surname: Yuan fullname: Yuan, Yixuan email: yxyuan.ee@cityu.edu.hk organization: City University of Hong Kong |
| BookMark | eNotjNFKwzAUQKMouM19gT7kB1pvkiZNfBtzbsJw4qavI21uRmRNSxsE_96CPp0DB86UXMU2IiH3DHLGwDwsP9_eJVda5xw4zwGUgQsyZUrJQplCiUsyYaBEpgwzN2Q-DF8AIDhjyugJWe9Dc3ikGxvdOcQT3XUYswETfW3DgNS3PX1qGxsiXTjbpfCNdI-NjSnUo5wajMmm0MZbcu3tecD5P2fk43l1WG6y7W79slxss8BBpKwqKuO8tqjBSwtOYAVM1ugKL6SQvBQcZVWNxThdKK5KIUFry72rdQ1azMjd3zcg4rHrQ2P7n6PRpVFj_QV6rk4g |
| CODEN | IEEPAD |
| ContentType | Conference Proceeding |
| DBID | 6IE 6IH CBEJK RIE RIO |
| DOI | 10.1109/CVPR52688.2022.00690 |
| DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Proceedings Order Plan (POP) 1998-present by volume IEEE Xplore All Conference Proceedings IEEE/IET Electronic Library (IEL) (UW System Shared) IEEE Proceedings Order Plans (POP) 1998-present |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE/IET Electronic Library (IEL) (UW System Shared) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Applied Sciences |
| EISBN | 1665469463 9781665469463 |
| EISSN | 1063-6919 |
| EndPage | 7031 |
| ExternalDocumentID | 9879608 |
| Genre | orig-research |
| GroupedDBID | 6IE 6IH 6IL 6IN AAWTH ABLEC ADZIZ ALMA_UNASSIGNED_HOLDINGS BEFXN BFFAM BGNUA BKEBE BPEOZ CBEJK CHZPO IEGSK IJVOP OCL RIE RIL RIO |
| ID | FETCH-LOGICAL-i203t-b4b9df8ae80f5a0d3eb015ced4f35352732e5bba0d9d84626735088a2fdc8c083 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 19 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000867754207029&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| IngestDate | Wed Aug 27 02:15:10 EDT 2025 |
| IsPeerReviewed | false |
| IsScholarly | true |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-i203t-b4b9df8ae80f5a0d3eb015ced4f35352732e5bba0d9d84626735088a2fdc8c083 |
| PageCount | 10 |
| ParticipantIDs | ieee_primary_9879608 |
| PublicationCentury | 2000 |
| PublicationDate | 2022-June |
| PublicationDateYYYYMMDD | 2022-06-01 |
| PublicationDate_xml | – month: 06 year: 2022 text: 2022-June |
| PublicationDecade | 2020 |
| PublicationTitle | Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) |
| PublicationTitleAbbrev | CVPR |
| PublicationYear | 2022 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| SSID | ssj0003211698 |
| Score | 2.405384 |
| Snippet | This paper studies a practical domain adaptive (DA) semantic segmentation problem where only pseudo-labeled target data is accessible through a black-box... |
| SourceID | ieee |
| SourceType | Publisher |
| StartPage | 7022 |
| SubjectTerms | Adaptation models Computational geometry Computational modeling Estimation grouping and shape analysis Representation learning Semantics Solid modeling Transfer/low-shot/long-tail learning; Deep learning architectures and techniques; Scene analysis and understanding; Segmentation |
| Title | SimT: Handling Open-set Noise for Domain Adaptive Semantic Segmentation |
| URI | https://ieeexplore.ieee.org/document/9879608 |
| WOSCitedRecordID | wos000867754207029&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV09T8MwED2VioGpQIv4lgdGTBMnjR02VCidqooW1K3yxxllaFI1Kb8fO43ahYXt5ESKdJH9nu177wAejHUor-KICrSGxiE3VFrDKVMY6jR0YaLqZhN8MhGLRTptweNeC4OIdfEZPvmwvss3hd76o7K-2x87wi2O4IhzvtNq7c9TIreTSVLRqOPCIO0Pv6Yf3szEF3Axb8uZ1AvvoYdKDSGjzv8-fgq9gxaPTPcocwYtzM-h05BH0kzNsgvvs2w1fyZj75rgXiS-UoSWWJFJkZVIHDclr8VKZjl5MXLtFzkyw5XLa6Zd8L1qNEh5Dz5Hb_PhmDZdEmjGgqiiKlapsUKiCOxABiZC5SBeo4lt5L1beMRwoJR7khpHNljCI0_KJLNGC-0Y2AW08yLHSyCJtIHgkhmH4bGROjXeLp4rLZi0KkmuoOvzslzvjDCWTUqu_x6-gROf-F1d1S20q80W7-BY_1RZubmv_94vdbecMw |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PT8IwFG4QTfSECsbf9uDRytaNrfNmUMSICxE03Eh_vJodthE2_PttxwIXL95euiVNXrN-X7v3fQ-hW6UNygvfIwy0Ir4bKsK1CgkV4MrINWEgqmYTYRyz2SwaN9DdRgsDAFXxGdzbsPqXr3K5sldlXXM-NoSb7aDdnu9Td63W2tyoeOYsE0Ss1se5TtTtf40_rJ2JLeGi1pgzqLbebReVCkQGrf9Nf4g6WzUeHm9w5gg1IDtGrZo-4vrjLNroZZKk0wc8tL4J5kVsa0VIASWO86QAbNgpfspTnmT4UfGF3ebwBFKT2USa4DutVUhZB30Onqf9Ian7JJCEOl5JhC8ipRkH5uged5QHwoC8BOVrz7q3hB6FnhDmSaQM3aBB6FlaxqlWkknDwU5QM8szOEU44NphIafKoLivuIyUNYwPhWSUaxEEZ6ht8zJfrK0w5nVKzv8evkH7w-n7aD56jd8u0IFdhHWV1SVqlssVXKE9-VMmxfK6WslfxoOfeg |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=proceeding&rft.title=Proceedings+%28IEEE+Computer+Society+Conference+on+Computer+Vision+and+Pattern+Recognition.+Online%29&rft.atitle=SimT%3A+Handling+Open-set+Noise+for+Domain+Adaptive+Semantic+Segmentation&rft.au=Guo%2C+Xiaoqing&rft.au=Liu%2C+Jie&rft.au=Liu%2C+Tongliang&rft.au=Yuan%2C+Yixuan&rft.date=2022-06-01&rft.pub=IEEE&rft.eissn=1063-6919&rft.spage=7022&rft.epage=7031&rft_id=info:doi/10.1109%2FCVPR52688.2022.00690&rft.externalDocID=9879608 |