mlsanityData to 7 Oct 2026

Part-aware Prototype Network for Few-shot Semantic Segmentation

arXiv 2007.06309 ↗First posted 13 Jul 2020cs.CVcited by 162

Not on the map. Why?

Abstract (arXiv)

Few-shot semantic segmentation aims to learn to segment new object classes with only a few annotated examples, which has a wide range of real-world applications. Most existing methods either focus on the restrictive setting of one-way few-shot segmentation or suffer from incomplete coverage of object regions. In this paper, we propose a novel few-shot semantic segmentation framework based on the prototype representation. Our key idea is to decompose the holistic class representation into a set of part-aware prototypes, capable of capturing diverse and fine-grained object features. In addition, we propose to leverage unlabeled data to enrich our part-aware prototypes, resulting in better modeling of intra-class variations of semantic objects. We develop a novel graph neural network model to generate and enhance the proposed part-aware prototypes based on labeled and unlabeled images. Extensive experimental evaluations on two benchmarks show that our method outperforms the prior art with a sizable margin.

Key facts. Cited by 162 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 32; 2022: 46; 2023: 38; 2024: 24; 2025: 16; 2026: 6.

162 papers.

Sort:

By area:

  1. 2022Language-driven Semantic Segmentationcited by 711
  2. 2022GroupViT: Semantic Segmentation Emerges from Text Supervisioncited by 529
  3. 2021Image Segmentation Using Text and Image Promptscited by 509
  4. 2022Visual Prompting via Image Inpaintingcited by 248
  5. 2021Adaptive Prototype Learning and Allocation for Few-Shot Segmentationcited by 207
  6. 2021Hypercorrelation Squeeze for Few-Shot Segmentationcited by 193
  7. 2023Towards Open Vocabulary Learning: A Surveycited by 165
  8. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 162
  9. 2021Few-Shot Segmentation via Cycle-Consistent Transformercited by 133
  10. 2022Learning What Not to Segment: A New Perspective on Few-Shot Segmentationcited by 120
  11. 2021Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformercited by 116
  12. 2022Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentationcited by 114
38 more
  1. 2021PartImageNet: A Large, High-Quality Dataset of Partscited by 107
  2. 2022Self-Support Few-Shot Semantic Segmentationcited by 96
  3. 2021Self-Guided and Cross-Guided Learning for Few-Shot Segmentationcited by 92
  4. 2021Repurposing GANs for One-shot Semantic Part Segmentationcited by 88
  5. 2022Self-supervised Image-specific Prototype Exploration for Weakly Supervised Semantic Segmentationcited by 87
  6. 2022FS6D: Few-Shot 6D Pose Estimation of Novel Objectscited by 81
  7. 2021Mining Latent Classes for Few-shot Segmentationcited by 69
  8. 2022Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentationcited by 65
  9. 2022Feature-Proxy Transformer for Few-Shot Segmentationcited by 58
  10. 2022Learning Non-target Knowledge for Few-shot Semantic Segmentationcited by 57
  11. 2021Learning Meta-class Memory for Few-Shot Semantic Segmentationcited by 56
  12. 2025Interpreting CLIP with Hierarchical Sparse Autoencoderscited by 54
  13. 2022Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuningcited by 50
  14. 2022Hybrid Relation Guided Set Matching for Few-shot Action Recognitioncited by 49
  15. 2023LLaFS: When Large Language Models Meet Few-Shot Segmentationcited by 48
  16. 2022Anomaly Detection-Inspired Few-Shot Medical Image Segmentation Through Self-Supervision With Supervoxelscited by 42
  17. 2022Intermediate Prototype Mining Transformer for Few-Shot Semantic Segmentationcited by 37
  18. 2021Few-shot Segmentation with Optimal Transport Matching and Message Flowcited by 36
  19. 2023MoLo: Motion-augmented Long-short Contrastive Learning for Few-shot Action Recognitioncited by 36
  20. 2022Compound Prototype Matching for Few-shot Action Recognitioncited by 35
  21. 2021PFENet++: Boosting Few-shot Semantic Segmentation with the Noise-filtered Context-aware Prior Maskcited by 31
  22. 2021Novel Class Discovery in Semantic Segmentationcited by 31
  23. 2022Unsupervised Video Object Segmentation via Prototype Memory Networkcited by 30
  24. 2023Universal Few-shot Learning of Dense Prediction Tasks with Visual Token Matchingcited by 29
  25. 2021Learning Implicit Temporal Alignment for Few-shot Video Classificationcited by 27
  26. 2022SPSN: Superpixel Prototype Sampling Network for RGB-D Salient Object Detectioncited by 26
  27. 2023Prototype Adaption and Projection for Few- and Zero-shot 3D Point Cloud Semantic Segmentationcited by 26
  28. 2022Integrative Few-Shot Learning for Classification and Segmentationcited by 25
  29. 2022Interclass Prototype Relation for Few-Shot Segmentationcited by 25
  30. 2022Q-Net: Query-Informed Few-Shot Medical Image Segmentationcited by 24
  31. 2021Anti-aliasing Semantic Reconstruction for Few-Shot Semantic Segmentationcited by 23
  32. 2022Doubly Deformable Aggregation of Covariance Matrices for Few-shot Segmentationcited by 23
  33. 2022A Strong Baseline for Generalized Few-Shot Semantic Segmentationcited by 22
  34. 2023FECANet: Boosting Few-Shot Semantic Segmentation with Feature-Enhanced Context-Aware Networkcited by 22
  35. 2023DifFSS: Diffusion Model for Few-Shot Semantic Segmentationcited by 22
  36. 2023Multi-Modal Prototypes for Open-World Semantic Segmentationcited by 22
  37. 2023UniRef++: Segment Every Reference Object in Spatial and Temporal Spacescited by 22
  38. 2024Adapt Before Comparison: A New Perspective on Cross-Domain Few-Shot Segmentationcited by 22

50 most cited of 162 All 162 (JSON)