CPEWS: Contextual Prototype-Based End-to-End Weakly Supervised Semantic Segmentation
Source abstract
Abstract
The primary challenge in weakly supervised semantic segmentation is effectively leveraging weak annotations while minimizing the performance gap compared to fully supervised methods. End-to-end model designs have gained signi... | Find, read and cite all the research you need on Tech Science Press
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Machine Learning and Data Classification · Software Engineering Research
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (44)
Show source-provided references
1. Anti-adversarially manipulated attributions for weakly and semi-supervised semantic segmentation
2. Akiva P, Dana K. Towards single stage weakly supervised semantic segmentation. arXiv:2106.10309. 2021.
3. BBAM: bounding box attribution map for weakly supervised semantic and instance segmentation
4. Zhang B, Xiao J, Zhao Y. Dynamic feature regularized loss for weakly supervised semantic segmentation. arXiv:2108.01296. 2021.
5. Ru · 2021 · 982
6. Affinity attention graph neural network for weakly supervised semantic segmentation10.1109/TPAMI.2021.3083269 ↗
7. Class re-activation maps for weakly-supervised semantic segmentation
8. Class tokens infusion for weakly supervised semantic segmentation
9. Breast lesion segmentation and classification using u-net saliency estimation and explainable residual convolutional neural network10.1142/S0218348X24400607 ↗
10. Efficient identification and classification of apple leaf diseases using lightweight vision transformer (ViT)10.1007/s43621-024-00307-1 ↗
11. Mitigating biased activation in weakly-supervised object localization via counterfactual learning
12. The pascal visual object classes challenge: a retrospective10.1007/s11263-014-0733-5 ↗
13. Microsoft COCO: common objects in context
14. Multi-granularity denoising and bidirectional alignment for weakly supervised semantic segmentation10.1109/TIP.2023.3275913 ↗
15. Separate and conquer: decoupling co-occurrence via decomposition and representation for weakly supervised semantic segmentation
16. Yang Z, Meng Y, Fu K, Wang S, Song Z. Tackling ambiguity from perspective of uncertainty inference and affinity diversification for weakly supervised semantic segmentation. arXiv:2404.08195. 2024.10.1109/TMM.2025.3613165 ↗
17. Learning affinity from attention: end-to-end weakly-supervised semantic segmentation with transformers
18. Sun W, Zhang J, Liu Z, Zhong Y, Barnes N. GETAM: gradient-weighted element-wise transformer attention map for weakly-supervised semantic segmentation. arXiv:2112.02841. 2021.
19. Multi-class token transformer for weakly supervised semantic segmentation
20. DuPL: dual student with trustworthy progressive learning for robust weakly supervised semantic segmentation
21. Rethinking semantic segmentation: a prototype view
22. Self-supervised image-specific prototype exploration for weakly supervised semantic segmentation
23. Regional semantic contrast and aggregation for weakly supervised semantic segmentation
24. Learning what not to segment: a new perspective on few-shot segmentation
25. Elimination of non-novel segments at multi-scale for few-shot segmentation
26. Hunting attributes: context prototype-aware learning for weakly supervised semantic segmentation
27. C-CAM: causal CAM for weakly supervised semantic segmentation on medical image
28. Railroad is not a train: saliency as pseudo-pixel supervision for weakly supervised semantic segmentation
29. CLIMS: cross language image matching for weakly supervised semantic segmentation
30. Weakly supervised semantic segmentation using out-of-distribution data
31. Frozen clip: a strong backbone for weakly supervised semantic segmentation
32. Jang S, Yun J, Kwon J, Lee E, Kim Y. DIAL: dense image-text alignment for weakly supervised semantic segmentation. arXiv:2409.15801. 2024.10.1007/978-3-031-72890-7_15 ↗
33. Ridnik T, Ben-Baruch E, Noy A, Zelnik-Manor L. ImageNet-21k pretraining for the masses. arXiv:2104.10972. 2021.
34. Token contrast for weakly-supervised semantic segmentation
35. Masked collaborative contrast for weakly supervised semantic segmentation
36. FPR: false positive rectification for weakly supervised semantic segmentation
37. Reducing information bottleneck for weakly supervised semantic segmentation
38. L2G: a simple local-to-global knowledge transfer framework for weakly supervised semantic segmentation
39. Weakly supervised semantic segmentation by pixel-to-prototype contrast
40. Weakly-supervised semantic segmentation with visual words learning and hybrid pooling10.1007/s11263-022-01586-9 ↗
41. Expansion and shrinkage of localization for weakly-supervised semantic segmentation
42. Learning self-supervised low-rank network for single-stage weakly and semi-supervised semantic segmentation10.1007/s11263-022-01590-z ↗
43. Self correspondence distillation for end-to-end weakly-supervised semantic segmentation
44. Training data-efficient image transformers & distillation through attention