mlsanityData to 7 Oct 2026

Feature Weighting and Boosting for Few-Shot Segmentation

arXiv 1909.13140 ↗First posted 28 Sep 2019cs.CVcited by 189

Not on the map. Why?

Abstract (arXiv)

This paper is about few-shot segmentation of foreground objects in images. We train a CNN on small subsets of training images, each mimicking the few-shot setting. In each subset, one image serves as the query and the other(s) as support image(s) with ground-truth segmentation. The CNN first extracts feature maps from the query and support images. Then, a class feature vector is computed as an average of the support's feature maps over the known foreground. Finally, the target object is segmented in the query image by using a cosine similarity between the class feature vector and the query's feature map. We make two contributions by: (1) Improving discriminativeness of features so their activations are high on the foreground and low elsewhere; and (2) Boosting inference with an ensemble of experts guided with the gradient of loss incurred when segmenting the support images in testing. Our evaluations on the PASCAL-5i and COCO-20i datasets demonstrate that we significantly outperform existing approaches.

Key facts. Cited by 189 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 35; 2022: 44; 2023: 35; 2024: 35; 2025: 28; 2026: 12.

189 papers.

Sort:

By area:

  1. 2022Language-driven Semantic Segmentationcited by 711
  2. 2022GroupViT: Semantic Segmentation Emerges from Text Supervisioncited by 529
  3. 2022Visual Prompting via Image Inpaintingcited by 248
  4. 2021Adaptive Prototype Learning and Allocation for Few-Shot Segmentationcited by 207
  5. 2021Hypercorrelation Squeeze for Few-Shot Segmentationcited by 193
  6. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 162
  7. 2023Matcher: Segment Anything with One Shot Using All-Purpose Feature Matchingcited by 142
  8. 2021Few-Shot Segmentation via Cycle-Consistent Transformercited by 133
  9. 2022Learning What Not to Segment: A New Perspective on Few-Shot Segmentationcited by 120
  10. 2021Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformercited by 116
  11. 2022Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentationcited by 114
  12. 2022Self-Support Few-Shot Semantic Segmentationcited by 96
38 more
  1. 2021Self-Guided and Cross-Guided Learning for Few-Shot Segmentationcited by 92
  2. 2023UniverSeg: Universal Medical Image Segmentationcited by 90
  3. 2023Hierarchical Dense Correlation Distillation for Few-Shot Segmentationcited by 84
  4. 2024VRP-SAM: SAM with Visual Reference Promptcited by 75
  5. 2021Mining Latent Classes for Few-shot Segmentationcited by 69
  6. 2022Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentationcited by 65
  7. 2022Feature-Proxy Transformer for Few-Shot Segmentationcited by 58
  8. 2022NeRF-Pose: A First-Reconstruct-Then-Regress Approach for Weakly-supervised 6D Object Pose Estimationcited by 57
  9. 2022Learning Non-target Knowledge for Few-shot Semantic Segmentationcited by 57
  10. 2021Learning Meta-class Memory for Few-Shot Semantic Segmentationcited by 56
  11. 2022Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuningcited by 50
  12. 2023LLaFS: When Large Language Models Meet Few-Shot Segmentationcited by 48
  13. 2022Dynamic Prototype Convolution Network for Few-Shot Semantic Segmentationcited by 43
  14. 2022Intermediate Prototype Mining Transformer for Few-Shot Semantic Segmentationcited by 37
  15. 2021Few-shot Segmentation with Optimal Transport Matching and Message Flowcited by 36
  16. 2024Bridge the Points: Graph-based Few-shot Segment Anything Semanticallycited by 35
  17. 2023Self-Calibrated Cross Attention Network for Few-Shot Segmentationcited by 32
  18. 2021PFENet++: Boosting Few-shot Semantic Segmentation with the Noise-filtered Context-aware Prior Maskcited by 31
  19. 2021Novel Class Discovery in Semantic Segmentationcited by 31
  20. 2022One-Shot Transfer of Affordance Regions? AffCorrs!cited by 31
  21. 2024Cross-Domain Few-Shot Segmentation via Iterative Support-Query Correspondence Miningcited by 30
  22. 2022Beyond the Prototype: Divide-and-conquer Proxies for Few-shot Segmentationcited by 28
  23. 2022Integrative Few-Shot Learning for Classification and Segmentationcited by 25
  24. 2022Interclass Prototype Relation for Few-Shot Segmentationcited by 25
  25. 2023MIANet: Aggregating Unbiased Instance and General Information for Few-Shot Semantic Segmentationcited by 25
  26. 2021All-Around Real Label Supervision: Cyclic Prototype Consistency Learning for Semi-supervised Medical Image Segmentationcited by 24
  27. 2023Distilling Self-Supervised Vision Transformers for Weakly-Supervised Few-Shot Classification & Segmentationcited by 24
  28. 2021Anti-aliasing Semantic Reconstruction for Few-Shot Semantic Segmentationcited by 23
  29. 2022Doubly Deformable Aggregation of Covariance Matrices for Few-shot Segmentationcited by 23
  30. 2022Mask Matching Transformer for Few-Shot Segmentationcited by 22
  31. 2023FECANet: Boosting Few-Shot Semantic Segmentation with Feature-Enhanced Context-Aware Networkcited by 22
  32. 2023DifFSS: Diffusion Model for Few-Shot Semantic Segmentationcited by 22
  33. 2023Multi-Modal Prototypes for Open-World Semantic Segmentationcited by 22
  34. 2022MSANet: Multi-Similarity and Attention Guidance for Boosting Few-Shot Segmentationcited by 21
  35. 2023Learning Expressive Prompting With Residuals for Vision Transformerscited by 21
  36. 2024Hybrid Mamba for Few-Shot Segmentationcited by 21
  37. 2024Tyche: Stochastic In-Context Learning for Medical Image Segmentationcited by 20
  38. 2024Rethinking Prior Information Generation with CLIP for Few-Shot Segmentationcited by 20

50 most cited of 189 All 189 (JSON)