mlsanityData to 7 Oct 2026

Background Noise Reduction of Attention Map for Weakly Supervised Semantic Segmentation

arXiv 2404.03394 ↗First posted 4 Apr 2024cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

In weakly-supervised semantic segmentation (WSSS) using only image-level class labels, a problem with CNN-based Class Activation Maps (CAM) is that they tend to activate the most discriminative local regions of objects. On the other hand, methods based on Transformers learn global features but suffer from the issue of background noise contamination. This paper focuses on addressing the issue of background noise in attention weights within the existing WSSS method based on Conformer, known as TransCAM. The proposed method successfully reduces background noise, leading to improved accuracy of pseudo labels. Experimental results demonstrate that our model achieves segmentation performance of 70.5% on the PASCAL VOC 2012 validation data, 71.1% on the test data, and 45.9% on MS COCO 2014 data, outperforming TransCAM in terms of segmentation performance.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 34 of its 43 references that are in the map. First posted on arXiv 4 Apr 2024.

Builds on

34 of 43 references.

References · 34

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  6. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  7. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  8. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,483
  9. 2014Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFscited by 552
  10. 2016ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentationcited by 330
  11. 2018Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentationcited by 321
  12. 2020Self-supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentationcited by 299
22 more
  1. 2015What's the Point: Semantic Segmentation with Point Supervisioncited by 297
  2. 2020Causal Intervention for Weakly-Supervised Semantic Segmentationcited by 229
  3. 2017Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-supervised Object and Action Localizationcited by 207
  4. 2017Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approachcited by 201
  5. 2016Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentationcited by 198
  6. 2016Wider or Deeper: Revisiting the ResNet Model for Visual Recognitioncited by 184
  7. 2021Conformer: Local Features Coupling Global Representations for Visual Recognitioncited by 164
  8. 2021TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localizationcited by 122
  9. 2021BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentationcited by 104
  10. 2022Self-supervised Image-specific Prototype Exploration for Weakly Supervised Semantic Segmentationcited by 87
  11. 2021Leveraging Auxiliary Tasks with Affinity Learning for Weakly Supervised Semantic Segmentationcited by 77
  12. 2021Complementary Patch for Weakly Supervised Semantic Segmentationcited by 75
  13. 2021Context Decoupling Augmentation for Weakly Supervised Semantic Segmentationcited by 69
  14. 2022Weakly Supervised Semantic Segmentation using Out-of-Distribution Datacited by 58
  15. 2022L2G: A Simple Local-to-Global Knowledge Transfer Framework for Weakly Supervised Semantic Segmentationcited by 57
  16. 2022Threshold Matters in WSSS: Manipulating the Activation for the Robust and Accurate Segmentation Model Against Thresholdscited by 37
  17. 2023Extracting Class Activation Maps from Non-Discriminative Features as wellcited by 30
  18. 2022TransCAM: Transformer Attention-based CAM Refinement for Weakly Supervised Semantic Segmentationcited by 26
  19. 2022Out-of-Candidate Rectification for Weakly Supervised Semantic Segmentationcited by 26
  20. 2023WeakTr: Exploring Plain Vision Transformer for Weakly-supervised Semantic Segmentationcited by 22
  21. 2022Anti-Adversarially Manipulated Attributions for Weakly Supervised Semantic Segmentation and Object Localizationcited by 12
  22. 2023MECPformer: Multi-estimations Complementary Patch with CNN-Transformers for Weakly Supervised Semantic Segmentationcited by 1

Built on by

Not cited yet.