mlsanityData to 14 Oct 2026

PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment

arXiv 1908.06391 ↗First posted 18 Aug 2019cs.CVcited by 449

Not on the map. Why?

Abstract (arXiv)

Despite the great progress made by deep CNNs in image semantic segmentation, they typically require a large number of densely-annotated images for training and are difficult to generalize to unseen object categories. Few-shot segmentation has thus been developed to learn to perform segmentation from only a few annotated examples. In this paper, we tackle the challenging few-shot segmentation problem from a metric learning perspective and present PANet, a novel prototype alignment network to better utilize the information of the support set. Our PANet learns class-specific prototype representations from a few support images within an embedding space and then performs segmentation over the query images through matching each pixel to the learned prototypes. With non-parametric metric learning, PANet offers high-quality prototypes that are representative for each semantic class and meanwhile discriminative for different classes. Moreover, PANet introduces a prototype alignment regularization between support and query. With this, PANet fully exploits knowledge from the support and provides better generalization on few-shot segmentation. Significantly, our model achieves the mIoU score of 48.1% and 55.7% on PASCAL-5i for 1-shot and 5-shot settings respectively, surpassing the state-of-the-art method by 1.8% and 8.6%.

Key facts. Cited by 449 papers in the map (data through 14 Oct 2026). First posted on arXiv 18 Aug 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 78; 2022: 74; 2023: 98; 2024: 83; 2025: 71; 2026: 45.

449 papers.

Sort:

By area:

  1. 2022Language-driven Semantic Segmentationcited by 717
  2. 2021Image Segmentation Using Text and Image Promptscited by 512
  3. 2023VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completioncited by 313
  4. 2021Adaptive Prototype Learning and Allocation for Few-Shot Segmentationcited by 207
  5. 2021Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentationcited by 203
  6. 2021Hypercorrelation Squeeze for Few-Shot Segmentationcited by 193
  7. 2023Towards Open Vocabulary Learning: A Surveycited by 166
  8. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 163
  9. 2024Medical SAM 2: Segment medical images as video via Segment Anything Model 2cited by 154
  10. 2022Rethinking Semantic Segmentation: A Prototype Viewcited by 140
  11. 2021Few-Shot Segmentation via Cycle-Consistent Transformercited by 133
  12. 2022Learning What Not to Segment: A New Perspective on Few-Shot Segmentationcited by 120
38 more
  1. 2021Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformercited by 116
  2. 2022Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentationcited by 114
  3. 2021Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representationscited by 96
  4. 2022Self-Support Few-Shot Semantic Segmentationcited by 96
  5. 2023Vision-Language Models in Remote Sensing: Current Progress and Future Trendscited by 93
  6. 2021Self-Guided and Cross-Guided Learning for Few-Shot Segmentationcited by 92
  7. 2023UniverSeg: Universal Medical Image Segmentationcited by 91
  8. 2021Repurposing GANs for One-shot Semantic Part Segmentationcited by 88
  9. 2022Self-supervised Image-specific Prototype Exploration for Weakly Supervised Semantic Segmentationcited by 87
  10. 2023Hierarchical Dense Correlation Distillation for Few-Shot Segmentationcited by 84
  11. 2021MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Imagescited by 78
  12. 2023Review of Large Vision Models and Visual Prompt Engineeringcited by 77
  13. 2024VRP-SAM: SAM with Visual Reference Promptcited by 75
  14. 2021Mining Latent Classes for Few-shot Segmentationcited by 69
  15. 2022Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentationcited by 65
  16. 2021Recurrent Mask Refinement for Few-Shot Medical Image Segmentationcited by 63
  17. 2023A Survey on Open-Vocabulary Detection and Segmentation: Past, Present, and Futurecited by 61
  18. 2022NeRF-Pose: A First-Reconstruct-Then-Regress Approach for Weakly-supervised 6D Object Pose Estimationcited by 58
  19. 2022Feature-Proxy Transformer for Few-Shot Segmentationcited by 58
  20. 2021A Closer Look at Self-training for Zero-Label Semantic Segmentationcited by 57
  21. 2022Learning Non-target Knowledge for Few-shot Semantic Segmentationcited by 57
  22. 2021Learning Meta-class Memory for Few-Shot Semantic Segmentationcited by 56
  23. 2024A Comprehensive Survey of Foundation Models in Medicinecited by 56
  24. 2021Factors of Influence for Transfer Learning across Diverse Appearance Domains and Task Typescited by 54
  25. 2021Exploiting a Joint Embedding Space for Generalized Zero-Shot Semantic Segmentationcited by 53
  26. 2023Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanismcited by 51
  27. 2022Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuningcited by 50
  28. 2023LLaFS: When Large Language Models Meet Few-Shot Segmentationcited by 48
  29. 2021Universal-Prototype Enhancing for Few-Shot Object Detectioncited by 43
  30. 2022Dynamic Prototype Convolution Network for Few-Shot Semantic Segmentationcited by 43
  31. 2023Exploring Effective Factors for Improving Visual In-Context Learningcited by 43
  32. 2024Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detectorcited by 43
  33. 2022Anomaly Detection-Inspired Few-Shot Medical Image Segmentation Through Self-Supervision With Supervoxelscited by 42
  34. 2022DAMO-YOLO : A Report on Real-Time Object Detection Designcited by 38
  35. 2023One-Prompt to Segment All Medical Imagescited by 38
  36. 2024In Defense of Lazy Visual Grounding for Open-Vocabulary Semantic Segmentationcited by 38
  37. 2022Intermediate Prototype Mining Transformer for Few-Shot Semantic Segmentationcited by 37
  38. 2021Few-shot Segmentation with Optimal Transport Matching and Message Flowcited by 36

50 most cited of 449 All 449 (JSON)