mlsanityData to 14 Oct 2026

Contrastive Prompt Clustering for Weakly Supervised Semantic Segmentation

arXiv 2508.17009 ↗First posted 23 Aug 2025cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Weakly Supervised Semantic Segmentation (WSSS) with image-level labels has gained attention for its cost-effectiveness. Most existing methods emphasize inter-class separation, often neglecting the shared semantics among related categories and lacking fine-grained discrimination. To address this, we propose Contrastive Prompt Clustering (CPC), a novel WSSS framework. CPC exploits Large Language Models (LLMs) to derive category clusters that encode intrinsic inter-class relationships, and further introduces a class-aware patch-level contrastive loss to enforce intra-class consistency and inter-class separation. This hierarchical design leverages clusters as coarse-grained semantic priors while preserving fine-grained boundaries, thereby reducing confusion among visually similar categories. Experiments on PASCAL VOC 2012 and MS COCO 2014 demonstrate that CPC surpasses existing state-of-the-art methods in WSSS.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 42 of its 67 references that are in the map. First posted on arXiv 23 Aug 2025.

Builds on

42 of 67 references.

References · 42

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  5. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,915
  6. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  7. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  8. 2021GPT Understands, Toocited by 716
  9. 2018Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentationcited by 321
  10. 2020AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Promptscited by 249
  11. 2017Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approachcited by 201
  12. 2016Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentationcited by 198
30 more
  1. 2023Prompt, Generate, then Cache: Cascade of Foundation Models makes Strong Few-shot Learnerscited by 152
  2. 2020Weakly-Supervised Semantic Segmentation via Sub-category Explorationcited by 145
  3. 2020Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentationcited by 144
  4. 2022Multi-class Token Transformer for Weakly Supervised Semantic Segmentationcited by 138
  5. 2021Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentationcited by 127
  6. 2022Learning Affinity from Attention: End-to-End Weakly-Supervised Semantic Segmentation with Transformerscited by 118
  7. 2021Non-Salient Region Object Mining for Weakly Supervised Semantic Segmentationcited by 95
  8. 2022Self-supervised Image-specific Prototype Exploration for Weakly Supervised Semantic Segmentationcited by 87
  9. 2021Weakly Supervised Semantic Segmentation by Pixel-to-Prototype Contrastcited by 85
  10. 2023Token Contrast for Weakly-Supervised Semantic Segmentationcited by 65
  11. 2022Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentationcited by 41
  12. 2023High-Resolution Document Shadow Removal via A Large-Scale Real-World Dataset and A Frequency-Aware Shadow Erasing Netcited by 36
  13. 2021Controllable Generation from Pre-trained Language Models via Inverse Promptingcited by 29
  14. 2023Self Correspondence Distillation for End-to-End Weakly-Supervised Semantic Segmentationcited by 26
  15. 2025FedSWA: Improving Generalization in Federated Learning with Highly Heterogeneous Data via Momentum-Based Stochastic Controlled Weight Averagingcited by 25
  16. 2023Image Augmentation with Controlled Diffusion for Weakly-Supervised Semantic Segmentationcited by 19
  17. 2024SFC: Shared Feature Calibration in Weakly Supervised Semantic Segmentationcited by 19
  18. 2024Dual-Hybrid Attention Network for Specular Highlight Removalcited by 18
  19. 2024TimeRAF: Retrieval-Augmented Foundation model for Zero-shot Time Series Forecastingcited by 17
  20. 2024Prompt Categories Cluster for Weakly Supervised Semantic Segmentationcited by 16
  21. 2024Adaptive Patch Contrast for Weakly Supervised Semantic Segmentationcited by 15
  22. 2024Image Augmentation Agent for Weakly Supervised Semantic Segmentationcited by 15
  23. 2023USAGE: A Unified Seed Area Generation Paradigm for Weakly Supervised Semantic Segmentationcited by 14
  24. 2022Anti-Adversarially Manipulated Attributions for Weakly Supervised Semantic Segmentation and Object Localizationcited by 12
  25. 2024High-Fidelity Document Stain Removal via A Large-Scale Real-World Dataset and A Memory-Augmented Transformercited by 12
  26. 2023Top-K Pooling with Patch Contrastive Learning for Weakly-Supervised Semantic Segmentationcited by 10
  27. 2022Learning Differential Operators for Interpretable Time Series Modelingcited by 7
  28. 2024Accurate Explanation Model for Image Classifiers using Class Association Embeddingcited by 6
  29. 2024A Weakly Supervised and Globally Explainable Learning Framework for Brain Tumor Segmentationcited by 6
  30. 2023Class-level Multiple Distributions Representation are Necessary for Semantic Segmentationcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026SQuaD-SQL: Efficient Text-to-SQL with Small Language Models via LLM-Guided Knowledge Distillationcited by 0