liu.seSearch for publications in DiVA
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
High-fidelity Pseudo-labels for Boosting Weakly-Supervised Segmentation
Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering. Husqvarna Grp, Sweden.ORCID iD: 0000-0002-3434-2522
Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.ORCID iD: 0000-0001-8761-4715
Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering. Univ KwaZulu Natal, South Africa.ORCID iD: 0000-0002-6096-3648
2024 (English)In: 2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Institute of Electrical and Electronics Engineers (IEEE), 2024, p. 999-1008Conference paper, Published paper (Refereed)
Abstract [en]

Image-level weakly-supervised semantic segmentation (WSSS) reduces the usually vast data annotation cost by surrogate segmentation masks during training. The typical approach involves training an image classification network using global average pooling (GAP) on convolutional feature maps. This enables the estimation of object locations based on class activation maps (CAMs), which identify the importance of image regions. The CAMs are then used to generate pseudo-labels, in the form of segmentation masks, to supervise a segmentation model in the absence of pixel-level ground truth. Our work is based on two techniques for improving CAMs; importance sampling, which is a substitute for GAP, and the feature similarity loss, which utilizes a heuristic that object contours almost always align with color edges in images. However, both are based on the multinomial posterior with softmax, and implicitly assume that classes are mutually exclusive, which turns out suboptimal in our experiments. Thus, we reformulate both techniques based on binomial posteriors of multiple independent binary problems. This has two benefits; their performance is improved and they become more general, resulting in an add-on method that can boost virtually any WSSS method. This is demonstrated on a wide variety of baselines on the PASCAL VOC dataset, improving the region similarity and contour quality of all implemented state-of-the-art methods. Experiments on the MS COCO dataset further show that our proposed add-on is well-suited for large-scale settings. Our code implementation is available at https://github.com/arvijj/hfpl.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE), 2024. p. 999-1008
Keywords [en]
weakly supervised, semantic segmentation, importance sampling, feature similarity, class activation maps
National Category
Computer Vision and Robotics (Autonomous Systems)
Identifiers
URN: urn:nbn:se:liu:diva-202446DOI: 10.1109/WACV57701.2024.00105OAI: oai:DiVA.org:liu-202446DiVA, id: diva2:1851761
Conference
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA, jan 3-8, 2024
Available from: 2024-04-15 Created: 2024-04-15 Last updated: 2024-04-24Bibliographically approved

Open Access in DiVA

fulltext(3780 kB)82 downloads
File information
File name FULLTEXT01.pdfFile size 3780 kBChecksum SHA-512
1fde454c5fbe9e3eb2ea5072e35fd187635ef63b8141c73be54a52139d44c68e482d1e3482ecaa606bf31df04d9ab0a8eb35f5f56bc135a53566b95602e8f8f8
Type fulltextMimetype application/pdf

Other links

Publisher's full text

Authority records

Jonnarth, ArviZhang, YushanFelsberg, Michael

Search in DiVA

By author/editor
Jonnarth, ArviZhang, YushanFelsberg, Michael
By organisation
Computer VisionFaculty of Science & Engineering
Computer Vision and Robotics (Autonomous Systems)

Search outside of DiVA

GoogleGoogle Scholar
Total: 82 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 284 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf