mlsanityData to 7 Oct 2026

MuSCLe: A Multi-Strategy Contrastive Learning Framework for Weakly Supervised Semantic Segmentation

arXiv 2201.07021 ↗First posted 18 Jan 2022cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Weakly supervised semantic segmentation (WSSS) has gained significant popularity since it relies only on weak labels such as image level annotations rather than pixel level annotations required by supervised semantic segmentation (SSS) methods. Despite drastically reduced annotation costs, typical feature representations learned from WSSS are only representative of some salient parts of objects and less reliable compared to SSS due to the weak guidance during training. In this paper, we propose a novel Multi-Strategy Contrastive Learning (MuSCLe) framework to obtain enhanced feature representations and improve WSSS performance by exploiting similarity and dissimilarity of contrastive sample pairs at image, region, pixel and object boundary levels. Extensive experiments demonstrate the effectiveness of our method and show that MuSCLe outperforms the current state-of-the-art on the widely used PASCAL VOC 2012 dataset.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 37 of its 49 references that are in the map. First posted on arXiv 18 Jan 2022.

Builds on

37 of 49 references.

References · 37

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  5. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  6. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  7. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  8. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  9. 2020Supervised Contrastive Learningcited by 2,803
  10. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  11. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,277
  12. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,424
25 more
  1. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,379
  2. 2015Unsupervised Visual Representation Learning by Context Predictioncited by 1,062
  3. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,018
  4. 2017Focal Loss for Dense Object Detectioncited by 749
  5. 2019Learning Representations by Maximizing Mutual Information Across Viewscited by 733
  6. 2019Data-Efficient Image Recognition with Contrastive Predictive Codingcited by 672
  7. 2019GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyondcited by 331
  8. 2016ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentationcited by 330
  9. 2018Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentationcited by 321
  10. 2019Deep Multi-modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challengescited by 313
  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. 2020Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learningcited by 297
  14. 2019Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relationscited by 245
  15. 2015BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentationcited by 238
  16. 2016Simple Does It: Weakly Supervised Instance and Semantic Segmentationcited by 226
  17. 2017Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approachcited by 201
  18. 2016Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentationcited by 198
  19. 2020PseudoSeg: Designing Pseudo Labels for Semantic Segmentationcited by 180
  20. 2019FickleNet: Weakly and Semi-supervised Semantic Image Segmentation using Stochastic Inferencecited by 162
  21. 2020Weakly-Supervised Semantic Segmentation via Sub-category Explorationcited by 145
  22. 2018Learning random-walk label propagation for weakly-supervised semantic segmentationcited by 101
  23. 2020Self-EMD: Self-Supervised Object Detection without ImageNetcited by 70
  24. 2017Improving Pairwise Ranking for Multi-label Image Classificationcited by 40
  25. 2013Large-scale Multi-label Text Classification - Revisiting Neural Networkscited by 35

Built on by

Not cited yet.