mlsanityData to 14 Oct 2026

Harmonizing Base and Novel Classes: A Class-Contrastive Approach for Generalized Few-Shot Segmentation

arXiv 2303.13724 ↗First posted 24 Mar 2023cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

Current methods for few-shot segmentation (FSSeg) have mainly focused on improving the performance of novel classes while neglecting the performance of base classes. To overcome this limitation, the task of generalized few-shot semantic segmentation (GFSSeg) has been introduced, aiming to predict segmentation masks for both base and novel classes. However, the current prototype-based methods do not explicitly consider the relationship between base and novel classes when updating prototypes, leading to a limited performance in identifying true categories. To address this challenge, we propose a class contrastive loss and a class relationship loss to regulate prototype updates and encourage a large distance between prototypes from different classes, thus distinguishing the classes from each other while maintaining the performance of the base classes. Our proposed approach achieves new state-of-the-art performance for the generalized few-shot segmentation task on PASCAL VOC and MS COCO datasets.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 45 of its 65 references that are in the map. First posted on arXiv 24 Mar 2023.

Builds on

45 of 65 references.

References · 45

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  3. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  4. 2016Pyramid Scene Parsing Networkcited by 2,479
  5. 2019Panoptic Feature Pyramid Networkscited by 645
  6. 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
  7. 2020Prior Guided Feature Enrichment Network for Few-Shot Segmentationcited by 271
  8. 2021Exploring Cross-Image Pixel Contrast for Semantic Segmentationcited by 242
  9. 2019Cross Attention Network for Few-shot Classificationcited by 219
  10. 2021Adaptive Prototype Learning and Allocation for Few-Shot Segmentationcited by 207
  11. 2021Hypercorrelation Squeeze for Few-Shot Segmentationcited by 193
  12. 2015Attention to Scale: Scale-aware Semantic Image Segmentationcited by 169
33 more
  1. 2020Part-aware Prototype Network for Few-shot Semantic Segmentationcited by 162
  2. 2019FSS-1000: A 1000-Class Dataset for Few-Shot Segmentationcited by 160
  3. 2018Task-Agnostic Meta-Learning for Few-shot Learningcited by 151
  4. 2020Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?cited by 135
  5. 2020Self-Supervision with Superpixels: Training Few-shot Medical Image Segmentation without Annotationcited by 128
  6. 2019Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learningcited by 121
  7. 2022Learning What Not to Segment: A New Perspective on Few-Shot Segmentationcited by 120
  8. 2021Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformercited by 116
  9. 2019Finding Task-Relevant Features for Few-Shot Learning by Category Traversalcited by 101
  10. 2020CRNet: Cross-Reference Networks for Few-Shot Segmentationcited by 101
  11. 2021Pixel Contrastive-Consistent Semi-Supervised Semantic Segmentationcited by 101
  12. 2022Self-Support Few-Shot Semantic Segmentationcited by 96
  13. 2020Contrastive Learning for Label-Efficient Semantic Segmentationcited by 93
  14. 2021Self-Guided and Cross-Guided Learning for Few-Shot Segmentationcited by 92
  15. 2021Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detectioncited by 80
  16. 2021Mining Latent Classes for Few-shot Segmentationcited by 69
  17. 2020Generalized Few-shot Semantic Segmentationcited by 59
  18. 2019Image Deformation Meta-Networks for One-Shot Learningcited by 56
  19. 2021Learning Meta-class Memory for Few-Shot Semantic Segmentationcited by 56
  20. 2021Few-shot Segmentation with Optimal Transport Matching and Message Flowcited by 36
  21. 2020BriNet: Towards Bridging the Intra-class and Inter-class Gaps in One-Shot Segmentationcited by 28
  22. 2022Beyond the Prototype: Divide-and-conquer Proxies for Few-shot Segmentationcited by 28
  23. 2020SimPropNet: Improved Similarity Propagation for Few-shot Image Segmentationcited by 27
  24. 2022Integrative Few-Shot Learning for Classification and Segmentationcited by 25
  25. 2021Anti-aliasing Semantic Reconstruction for Few-Shot Semantic Segmentationcited by 23
  26. 2022MSANet: Multi-Similarity and Attention Guidance for Boosting Few-Shot Segmentationcited by 21
  27. 2020Self-Supervised Tuning for Few-Shot Segmentationcited by 17
  28. 2021Few-Shot Segmentation with Global and Local Contrastive Learningcited by 17
  29. 2021Cross-Image Region Mining with Region Prototypical Network for Weakly Supervised Segmentationcited by 13
  30. 2022Distilling Knowledge from Object Classification to Aesthetics Assessmentcited by 12
  31. 2021APANet: Adaptive Prototypes Alignment Network for Few-Shot Semantic Segmentationcited by 11
  32. 2021Few-Shot Video Object Detectioncited by 7
  33. 2022CRCNet: Few-shot Segmentation with Cross-Reference and Region-Global Conditional Networkscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 3; 2025: 2; 2026: 1.

8 papers.

  1. 2024Networking Systems for Video Anomaly Detection: A Tutorial and Surveycited by 21
  2. 2023LCReg: Long-Tailed Image Classification with Latent Categories based Recognitioncited by 9
  3. 2023Integrating Large Pre-trained Models into Multimodal Named Entity Recognition with Evidential Fusioncited by 4
  4. 2024SCMix: Stochastic Compound Mixing for Open Compound Domain Adaptation in Semantic Segmentationcited by 2
  5. 2024Enhancing Incomplete Multi-modal Brain Tumor Segmentation with Intra-modal Asymmetry and Inter-modal Dependencycited by 1
  6. 2026Make It Up: Fake Images, Real Gains in Generalized Few-shot Semantic Segmentationcited by 1
  7. 2025Uncertainty Awareness on Unsupervised Domain Adaptation for Time Series Datacited by 0
  8. 2025Integrating SAM Supervision for 3D Weakly Supervised Point Cloud Segmentationcited by 0