mlsanityData to 7 Oct 2026

MSI: Maximize Support-Set Information for Few-Shot Segmentation

arXiv 2212.04673 ↗First posted 9 Dec 2022cs.CVcited by 18

Not on the map. Why?

Abstract (arXiv)

FSS(Few-shot segmentation) aims to segment a target class using a small number of labeled images(support set). To extract information relevant to the target class, a dominant approach in best-performing FSS methods removes background features using a support mask. We observe that this feature excision through a limiting support mask introduces an information bottleneck in several challenging FSS cases, e.g., for small targets and/or inaccurate target boundaries. To this end, we present a novel method(MSI), which maximizes the support-set information by exploiting two complementary sources of features to generate super correlation maps. We validate the effectiveness of our approach by instantiating it into three recent and strong FSS methods. Experimental results on several publicly available FSS benchmarks show that our proposed method consistently improves performance by visible margins and leads to faster convergence. Our code and trained models are available at: https://github.com/moonsh/MSI-Maximize-Support-Set-Information

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 33 of its 43 references that are in the map. First posted on arXiv 9 Dec 2022.

Builds on

33 of 43 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  6. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  7. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  8. 2016Pyramid Scene Parsing Networkcited by 2,472
  9. 2018Attention U-Net: Learning Where to Look for the Pancreascited by 1,420
  10. 2018Albumentations: fast and flexible image augmentationscited by 558
  11. 2017Understanding the Effective Receptive Field in Deep Convolutional Neural Networkscited by 549
  12. 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
21 more
  1. 2017One-Shot Learning for Semantic Segmentationcited by 337
  2. 2020Prior Guided Feature Enrichment Network for Few-Shot Segmentationcited by 271
  3. 2019CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learningcited by 217
  4. 2021Adaptive Prototype Learning and Allocation for Few-Shot Segmentationcited by 207
  5. 2021Hypercorrelation Squeeze for Few-Shot Segmentationcited by 193
  6. 2020Prototype Mixture Models for Few-shot Semantic Segmentationcited by 190
  7. 2019Feature Weighting and Boosting for Few-Shot Segmentationcited by 189
  8. 2018SG-One: Similarity Guidance Network for One-Shot Semantic Segmentationcited by 169
  9. 2019FSS-1000: A 1000-Class Dataset for Few-Shot Segmentationcited by 160
  10. 2020Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?cited by 135
  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
  13. 2021Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformercited by 116
  14. 2022Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentationcited by 114
  15. 2021CATs: Cost Aggregation Transformers for Visual Correspondencecited by 77
  16. 2022Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentationcited by 65
  17. 2021Few-shot Segmentation with Optimal Transport Matching and Message Flowcited by 36
  18. 2022Integrative Few-Shot Learning for Classification and Segmentationcited by 25
  19. 2021Cost Aggregation Is All You Need for Few-Shot Segmentationcited by 16
  20. 2021Global Pooling, More than Meets the Eye: Position Information is Encoded Channel-Wise in CNNscited by 12
  21. 2022HM: Hybrid Masking for Few-Shot Segmentationcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 8; 2025: 7; 2026: 2.

18 papers.

Sort:

By area:

  1. 2023LLaFS: When Large Language Models Meet Few-Shot Segmentationcited by 48
  2. 2024Rethinking Prior Information Generation with CLIP for Few-Shot Segmentationcited by 20
  3. 2025Not All Data Are Unlearned Equallycited by 12
  4. 2025SANSA: Unleashing the Hidden Semantics in SAM2 for Few-Shot Segmentationcited by 8
  5. 2025DSV-LFS: Unifying LLM-Driven Semantic Cues with Visual Features for Robust Few-Shot Segmentationcited by 6
  6. 2024Group-On: Boosting One-Shot Segmentation with Supportive Querycited by 3
  7. 2024Beyond Mask: Rethinking Guidance Types in Few-shot Segmentationcited by 3
  8. 2024High-Performance Few-Shot Segmentation with Foundation Models: An Empirical Studycited by 3
  9. 2024Embedding Generalized Semantic Knowledge into Few-Shot Remote Sensing Segmentationcited by 2
  10. 2025UINO-FSS: Unifying Representation Learning and Few-shot Segmentation via Hierarchical Distillation and Mamba-HyperCorrelationcited by 1
  11. 2025Object-level Correlation for Few-Shot Segmentationcited by 1
  12. 2025Unbiased Semantic Decoding with Vision Foundation Models for Few-shot Segmentationcited by 1
6 more
  1. 2024Judging from Support-set: A New Way to Utilize Few-Shot Segmentation for Segmentation Refinement Processcited by 0
  2. 2024FCC: Fully Connected Correlation for One-Shot Segmentationcited by 0
  3. 2024Generative Model-Based Fusion for Improved Few-Shot Semantic Segmentation of Infrared Imagescited by 0
  4. 2025Efficient Masked Attention Transformer for Few-Shot Classification and Segmentationcited by 0
  5. 2026Cross-Domain Few-Shot Segmentation via Multi-view Progressive Adaptationcited by 0
  6. 2026Exploiting Target Knowledge from MLLMs for Robust Few-Shot Segmentationcited by 0