mlsanityData to 7 Oct 2026

Rethinking Saliency-Guided Weakly-Supervised Semantic Segmentation

arXiv 2404.00918 ↗First posted 1 Apr 2024cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper presents a fresh perspective on the role of saliency maps in weakly-supervised semantic segmentation (WSSS) and offers new insights and research directions based on our empirical findings. We conduct comprehensive experiments and observe that the quality of the saliency map is a critical factor in saliency-guided WSSS approaches. Nonetheless, we find that the saliency maps used in previous works are often arbitrarily chosen, despite their significant impact on WSSS. Additionally, we observe that the choice of the threshold, which has received less attention before, is non-trivial in WSSS. To facilitate more meaningful and rigorous research for saliency-guided WSSS, we introduce textttWSSS-BED, a standardized framework for conducting research under unified conditions. textttWSSS-BED provides various saliency maps and activation maps for seven WSSS methods, as well as saliency maps from unsupervised salient object detection models.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 75 of its 95 references that are in the map. First posted on arXiv 1 Apr 2024.

Builds on

75 of 95 references.

References · 75

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  6. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  7. 2022A ConvNet for the 2020scited by 3,545
  8. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  9. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  10. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
  11. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  12. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,338
38 more
  1. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  2. 2018Unified Perceptual Parsing for Scene Understandingcited by 1,265
  3. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,215
  4. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,148
  5. 2020In Search of Lost Domain Generalizationcited by 1,042
  6. 2021Segmenter: Transformer for Semantic Segmentationcited by 855
  7. 2019Segmentation Transformer: Object-Contextual Representations for Semantic Segmentationcited by 573
  8. 2022Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentationcited by 341
  9. 2016ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentationcited by 330
  10. 2018Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentationcited by 321
  11. 2020Self-supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentationcited by 299
  12. 2015What's the Point: Semantic Segmentation with Point Supervisioncited by 297
  13. 2020Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixupcited by 260
  14. 2020Causal Intervention for Weakly-Supervised Semantic Segmentationcited by 229
  15. 2016Simple Does It: Weakly Supervised Instance and Semantic Segmentationcited by 226
  16. 2019A Simple Pooling-Based Design for Real-Time Salient Object Detectioncited by 211
  17. 2021K-Net: Towards Unified Image Segmentationcited by 211
  18. 2017Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approachcited by 201
  19. 2016Deeply supervised salient object detection with short connectionscited by 196
  20. 2015Visual Saliency Based on Multiscale Deep Featurescited by 185
  21. 2016Wider or Deeper: Revisiting the ResNet Model for Visual Recognitioncited by 184
  22. 2021Visual Saliency Transformercited by 175
  23. 2020Single-Stage Semantic Segmentation from Image Labelscited by 167
  24. 2019FickleNet: Weakly and Semi-supervised Semantic Image Segmentation using Stochastic Inferencecited by 162
  25. 2018Revisiting Dilated Convolution: A Simple Approach for Weakly- and Semi- Supervised Semantic Segmentationcited by 145
  26. 2020Weakly-Supervised Semantic Segmentation via Sub-category Explorationcited by 145
  27. 2020Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentationcited by 144
  28. 2022Multi-class Token Transformer for Weakly Supervised Semantic Segmentationcited by 138
  29. 2021Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentationcited by 134
  30. 2019Pyramid Feature Attention Network for Saliency detectioncited by 128
  31. 2021Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentationcited by 127
  32. 2022Learning Affinity from Attention: End-to-End Weakly-Supervised Semantic Segmentation with Transformerscited by 118
  33. 2020Evaluating Weakly Supervised Object Localization Methods Rightcited by 104
  34. 2021BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentationcited by 104
  35. 2018Self-Erasing Network for Integral Object Attentioncited by 95
  36. 2021Non-Salient Region Object Mining for Weakly Supervised Semantic Segmentationcited by 95
  37. 2021Multi-Scale High-Resolution Vision Transformer for Semantic Segmentationcited by 92
  38. 2014Salient Object Detection: A Discriminative Regional Feature Integration Approachcited by 89

50 most cited of 75 All 75 (JSON)

Built on by

Not cited yet.