Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
133 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

SFC: Shared Feature Calibration in Weakly Supervised Semantic Segmentation (2401.11719v1)

Published 22 Jan 2024 in cs.CV and cs.AI

Abstract: Image-level weakly supervised semantic segmentation has received increasing attention due to its low annotation cost. Existing methods mainly rely on Class Activation Mapping (CAM) to obtain pseudo-labels for training semantic segmentation models. In this work, we are the first to demonstrate that long-tailed distribution in training data can cause the CAM calculated through classifier weights over-activated for head classes and under-activated for tail classes due to the shared features among head- and tail- classes. This degrades pseudo-label quality and further influences final semantic segmentation performance. To address this issue, we propose a Shared Feature Calibration (SFC) method for CAM generation. Specifically, we leverage the class prototypes that carry positive shared features and propose a Multi-Scaled Distribution-Weighted (MSDW) consistency loss for narrowing the gap between the CAMs generated through classifier weights and class prototypes during training. The MSDW loss counterbalances over-activation and under-activation by calibrating the shared features in head-/tail-class classifier weights. Experimental results show that our SFC significantly improves CAM boundaries and achieves new state-of-the-art performances. The project is available at https://github.com/Barrett-python/SFC.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (46)
  1. Weakly supervised learning of instance segmentation with inter-pixel relations. In CVPR.
  2. Saving 100x Storage: Prototype Replay for Reconstructing Training Sample Distribution in Class-Incremental Semantic Segmentation. In NeurIPS.
  3. DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs. PAMI, 40: 834–848.
  4. Self-supervised image-specific prototype exploration for weakly supervised semantic segmentation. In CVPR.
  5. Class re-activation maps for weakly-supervised semantic segmentation. In CVPR.
  6. Imagenet: A large-scale hierarchical image database. In CVPR.
  7. Weakly supervised semantic segmentation by pixel-to-prototype contrast. In CVPR.
  8. The pascal visual object classes (voc) challenge. IJCV, 88: 303–338.
  9. Semantic contours from inverse detectors. In ICCV.
  10. Deep residual learning for image recognition. In CVPR.
  11. Batchformer: Learning to explore sample relationships for robust representation learning. In CVPR.
  12. Efficient inference in fully connected crfs with gaussian edge potentials. In NeurIPS.
  13. Reducing information bottleneck for weakly supervised semantic segmentation. In NeurIPS.
  14. Anti-adversarially manipulated attributions for weakly and semi-supervised semantic segmentation. In CVPR.
  15. Threshold matters in WSSS: manipulating the activation for the robust and accurate segmentation model against thresholds. In CVPR.
  16. Railroad is not a train: Saliency as pseudo-pixel supervision for weakly supervised semantic segmentation. In CVPR.
  17. Expansion and shrinkage of localization for weakly-supervised semantic segmentation. In NeurIPS.
  18. Group based deep shared feature learning for fine-grained image classification. arXiv preprint arXiv:2004.01817.
  19. Group-wise semantic mining for weakly supervised semantic segmentation. In AAAI.
  20. Microsoft coco: Common objects in context. In ECCV.
  21. Clip is also an efficient segmenter: A text-driven approach for weakly supervised semantic segmentation. In CVPR.
  22. Infrared and Visible Cross-Modal Image Retrieval Through Shared Features. TCSVT, 31: 4485–4496.
  23. Fully convolutional networks for semantic segmentation. In CVPR.
  24. Image segmentation using deep learning: A survey. PAMI, 44(7): 3523–3542.
  25. Object-part attention model for fine-grained image classification. TIP, 27(3): 1487–1500.
  26. Mining cross-image semantics for weakly supervised semantic segmentation. In ECCV.
  27. Equalization loss v2: A new gradient balance approach for long-tailed object detection. In CVPR.
  28. Proper reuse of image classification features improves object detection. In CVPR, 13628–13637.
  29. Self-supervised equivariant attention mechanism for weakly supervised semantic segmentation. In CVPR.
  30. Distribution-balanced loss for multi-label classification in long-tailed datasets. In ECCV.
  31. CLIMS: cross language image matching for weakly supervised semantic segmentation. In CVPR.
  32. Leveraging auxiliary tasks with affinity learning for weakly supervised semantic segmentation. In CVPR.
  33. Multi-class token transformer for weakly supervised semantic segmentation. In CVPR.
  34. Self correspondence distillation for end-to-end weakly-supervised semantic segmentation. In AAAI.
  35. AutoBD: Automated bi-level description for scalable fine-grained visual categorization. TIP, 27(1): 10–23.
  36. Non-salient region object mining for weakly supervised semantic segmentation. In CVPR.
  37. Adversarial erasing framework via triplet with gated pyramid pooling layer for weakly supervised semantic segmentation. In ECCV.
  38. Affinity attention graph neural network for weakly supervised semantic segmentation. PAMI, 44(11): 8082–8096.
  39. Credible Dual-Expert Learning for Weakly Supervised Semantic Segmentation. IJCV, 131: 1892 – 1908.
  40. Causal intervention for weakly-supervised semantic segmentation. In NeurIPS.
  41. Complementary patch for weakly supervised semantic segmentation. In ICCV.
  42. SLCA: Slow Learner with Classifier Alignment for Continual Learning on a Pre-trained Model. arXiv preprint arXiv:2303.05118.
  43. Mining Unseen Classes via Regional Objectness: A Simple Baseline for Incremental Segmentation. NeurIPS, 35: 24340–24353.
  44. Learning multi-attention convolutional neural network for fine-grained image recognition. In ICCV.
  45. Learning deep features for discriminative localization. In CVPR.
  46. CTP: Towards Vision-Language Continual Pretraining via Compatible Momentum Contrast and Topology Preservation. In ICCV, 22257–22267.
Citations (8)

Summary

We haven't generated a summary for this paper yet.

Github Logo Streamline Icon: https://streamlinehq.com

GitHub