mlsanityData to 14 Oct 2026

Eliminating Feature Ambiguity for Few-Shot Segmentation

arXiv 2407.09842 ↗First posted 13 Jul 2024cs.CVcited by 19

Not on the map. Why?

Abstract (arXiv)

Recent advancements in few-shot segmentation (FSS) have exploited pixel-by-pixel matching between query and support features, typically based on cross attention, which selectively activate query foreground (FG) features that correspond to the same-class support FG features. However, due to the large receptive fields in deep layers of the backbone, the extracted query and support FG features are inevitably mingled with background (BG) features, impeding the FG-FG matching in cross attention. Hence, the query FG features are fused with less support FG features, i.e., the support information is not well utilized. This paper presents a novel plug-in termed ambiguity elimination network (AENet), which can be plugged into any existing cross attention-based FSS methods. The main idea is to mine discriminative query FG regions to rectify the ambiguous FG features, increasing the proportion of FG information, so as to suppress the negative impacts of the doped BG features. In this way, the FG-FG matching is naturally enhanced. We plug AENet into three baselines CyCTR, SCCAN and HDMNet for evaluation, and their scores are improved by large margins, e.g., the 1-shot performance of SCCAN can be improved by 3.0%+ on both PASCAL-5i and COCO-20i. The code is available at https://github.com/Sam1224/AENet.

Key facts. Cited by 19 papers in the map (data through 14 Oct 2026). Builds on 42 of its 53 references that are in the map. First posted on arXiv 13 Jul 2024.

Builds on

42 of 53 references.

References · 42

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  5. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  6. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  7. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  8. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  9. 2016Pyramid Scene Parsing Networkcited by 2,479
  10. 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
  11. 2017One-Shot Learning for Semantic Segmentationcited by 337
  12. 2020Prior Guided Feature Enrichment Network for Few-Shot Segmentationcited by 271
30 more
  1. 2019CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learningcited by 217
  2. 2021Adaptive Prototype Learning and Allocation for Few-Shot Segmentationcited by 207
  3. 2019Feature Weighting and Boosting for Few-Shot Segmentationcited by 189
  4. 2014Simultaneous Detection and Segmentationcited by 159
  5. 2022Rethinking Semantic Segmentation: A Prototype Viewcited by 140
  6. 2021Few-Shot Segmentation via Cycle-Consistent Transformercited by 133
  7. 2017A Review on Deep Learning Techniques Applied to Semantic Segmentationcited by 122
  8. 2022Learning What Not to Segment: A New Perspective on Few-Shot Segmentationcited by 120
  9. 2022Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentationcited by 114
  10. 2022Self-Support Few-Shot Semantic Segmentationcited by 96
  11. 2021Self-Guided and Cross-Guided Learning for Few-Shot Segmentationcited by 92
  12. 2023Hierarchical Dense Correlation Distillation for Few-Shot Segmentationcited by 84
  13. 2022Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentationcited by 65
  14. 2022Learning Non-target Knowledge for Few-shot Semantic Segmentationcited by 57
  15. 2022Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuningcited by 50
  16. 2023LLaFS: When Large Language Models Meet Few-Shot Segmentationcited by 48
  17. 2022Dynamic Prototype Convolution Network for Few-Shot Semantic Segmentationcited by 43
  18. 2023Self-Calibrated Cross Attention Network for Few-Shot Segmentationcited by 32
  19. 2021PFENet++: Boosting Few-shot Semantic Segmentation with the Noise-filtered Context-aware Prior Maskcited by 31
  20. 2022Beyond the Prototype: Divide-and-conquer Proxies for Few-shot Segmentationcited by 28
  21. 2022Interclass Prototype Relation for Few-Shot Segmentationcited by 25
  22. 2023MIANet: Aggregating Unbiased Instance and General Information for Few-Shot Semantic Segmentationcited by 25
  23. 2023Distilling Self-Supervised Vision Transformers for Weakly-Supervised Few-Shot Classification & Segmentationcited by 24
  24. 2022Doubly Deformable Aggregation of Covariance Matrices for Few-shot Segmentationcited by 23
  25. 2022Mask Matching Transformer for Few-Shot Segmentationcited by 22
  26. 2023FECANet: Boosting Few-Shot Semantic Segmentation with Feature-Enhanced Context-Aware Networkcited by 22
  27. 2022MSANet: Multi-Similarity and Attention Guidance for Boosting Few-Shot Segmentationcited by 21
  28. 2023Relevant Intrinsic Feature Enhancement Network for Few-Shot Semantic Segmentationcited by 11
  29. 2023Adaptive FSS: A Novel Few-Shot Segmentation Framework via Prototype Enhancementcited by 10
  30. 2023Task-Disruptive Background Suppression for Few-Shot Segmentationcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 11; 2026: 7.

19 papers.

Sort:

By area:

  1. 2024Hybrid Mamba for Few-Shot Segmentationcited by 21
  2. 2025Unlocking the Power of SAM 2 for Few-Shot Segmentationcited by 11
  3. 2025SANSA: Unleashing the Hidden Semantics in SAM2 for Few-Shot Segmentationcited by 8
  4. 2025MOVE: Motion-Guided Few-Shot Video Object Segmentationcited by 6
  5. 2025SAMITE: Position Prompted SAM2 with Calibrated Memory for Visual Object Trackingcited by 5
  6. 2026Few-Shot Semantic Segmentation Meets SAM3cited by 3
  7. 2025UINO-FSS: Unifying Representation Learning and Few-shot Segmentation via Hierarchical Distillation and Mamba-HyperCorrelationcited by 1
  8. 2025Balancing Conservatism and Aggressiveness: Prototype-Affinity Hybrid Network for Few-Shot Segmentationcited by 1
  9. 2025Object-level Correlation for Few-Shot Segmentationcited by 1
  10. 2025Unbiased Semantic Decoding with Vision Foundation Models for Few-shot Segmentationcited by 1
  11. 2026Unify the Views: View-Consistent Prototype Learning for Few-Shot Segmentationcited by 1
  12. 2026Training-free Cross-domain Few-shot Segmentation via Robust Semantic Representation and Matchingcited by 1
7 more
  1. 2025Inter- and Intra-image Refinement for Few Shot Segmentationcited by 0
  2. 2025Object-Centric Cropping for Visual Few-Shot Classificationcited by 0
  3. 2025Beyond Visual Cues: Leveraging General Semantics as Support for Few-Shot Segmentationcited by 0
  4. 2026Cross-Domain Few-Shot Segmentation via Multi-view Progressive Adaptationcited by 0
  5. 2026Hierarchical Spatial and Channel Aggregation for Cross-domain Few-shot Segmentationcited by 0
  6. 2026GeoFlow: Geo-Aware Modeling of Inter-Area Relationships in Origin-Destination Flow Prediction and Generationcited by 0
  7. 2026Exploiting Target Knowledge from MLLMs for Robust Few-Shot Segmentationcited by 0