mlsanityData to 7 Oct 2026

MSANet: Multi-Similarity and Attention Guidance for Boosting Few-Shot Segmentation

arXiv 2206.09667 ↗First posted 20 Jun 2022cs.CVcited by 21

Not on the map. Why?

Abstract (arXiv)

Few-shot segmentation aims to segment unseen-class objects given only a handful of densely labeled samples. Prototype learning, where the support feature yields a singleor several prototypes by averaging global and local object information, has been widely used in FSS. However, utilizing only prototype vectors may be insufficient to represent the features for all training data. To extract abundant features and make more precise predictions, we propose a Multi-Similarity and Attention Network (MSANet) including two novel modules, a multi-similarity module and an attention module. The multi-similarity module exploits multiple feature-maps of support images and query images to estimate accurate semantic relationships. The attention module instructs the network to concentrate on class-relevant information. The network is tested on standard FSS datasets, PASCAL-5i 1-shot, PASCAL-5i 5-shot, COCO-20i 1-shot, and COCO-20i 5-shot. The MSANet with the backbone of ResNet-101 achieves the state-of-the-art performance for all 4-benchmark datasets with mean intersection over union (mIoU) of 69.13%, 73.99%, 51.09%, 56.80%, respectively. Code is available at https://github.com/AIVResearch/MSANet

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 52 of its 67 references that are in the map. First posted on arXiv 20 Jun 2022.

Builds on

52 of 67 references.

References · 52

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2017Mask R-CNNcited by 7,259
  6. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  7. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  8. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  9. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  10. 2016Pyramid Scene Parsing Networkcited by 2,472
  11. 2016Matching Networks for One Shot Learningcited by 2,246
  12. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,483
38 more
  1. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  2. 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,128
  3. 2018CCNet: Criss-Cross Attention for Semantic Segmentationcited by 717
  4. 2016RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentationcited by 463
  5. 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
  6. 2019YOLACT: Real-time Instance Segmentationcited by 441
  7. 2017One-Shot Learning for Semantic Segmentationcited by 337
  8. 2016ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentationcited by 330
  9. 2020Prior Guided Feature Enrichment Network for Few-Shot Segmentationcited by 271
  10. 2019CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learningcited by 217
  11. 2017Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Networkcited by 208
  12. 2021Adaptive Prototype Learning and Allocation for Few-Shot Segmentationcited by 207
  13. 2019CenterMask : Real-Time Anchor-Free Instance Segmentationcited by 200
  14. 2021Hypercorrelation Squeeze for Few-Shot Segmentationcited by 193
  15. 2020Prototype Mixture Models for Few-shot Semantic Segmentationcited by 190
  16. 2019Feature Weighting and Boosting for Few-Shot Segmentationcited by 189
  17. 2019PolarMask: Single Shot Instance Segmentation with Polar Representationcited by 188
  18. 2018Neighbourhood Consensus Networkscited by 173
  19. 2018SG-One: Similarity Guidance Network for One-Shot Semantic Segmentationcited by 169
  20. 2020Part-aware Prototype Network for Few-shot Semantic Segmentationcited by 162
  21. 2018Task-Agnostic Meta-Learning for Few-shot Learningcited by 151
  22. 2019GLU-Net: Global-Local Universal Network for Dense Flow and Correspondencescited by 139
  23. 2020Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?cited by 135
  24. 2021Few-Shot Segmentation via Cycle-Consistent Transformercited by 133
  25. 2022Learning What Not to Segment: A New Perspective on Few-Shot Segmentationcited by 120
  26. 2021Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformercited by 116
  27. 2019Finding Task-Relevant Features for Few-Shot Learning by Category Traversalcited by 101
  28. 2020CRNet: Cross-Reference Networks for Few-Shot Segmentationcited by 101
  29. 2021Self-Guided and Cross-Guided Learning for Few-Shot Segmentationcited by 92
  30. 2019YOLACT++: Better Real-time Instance Segmentationcited by 84
  31. 2015Proposal Flowcited by 57
  32. 2019Image Deformation Meta-Networks for One-Shot Learningcited by 56
  33. 2019Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Featurescited by 56
  34. 2021Learning Meta-class Memory for Few-Shot Semantic Segmentationcited by 56
  35. 2020Learning to Compose Hypercolumns for Visual Correspondencecited by 53
  36. 2020Correspondence Networks with Adaptive Neighbourhood Consensuscited by 42
  37. 2021Anti-aliasing Semantic Reconstruction for Few-Shot Semantic Segmentationcited by 23
  38. 2021Cost Aggregation Is All You Need for Few-Shot Segmentationcited by 16

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year

Citing papers per year: 2023: 12; 2024: 7; 2025: 2.

21 papers.

Sort:

By area:

  1. 2023Matcher: Segment Anything with One Shot Using All-Purpose Feature Matchingcited by 142
  2. 2023Self-Calibrated Cross Attention Network for Few-Shot Segmentationcited by 32
  3. 2023Universal Few-shot Learning of Dense Prediction Tasks with Visual Token Matchingcited by 29
  4. 2024Hybrid Mamba for Few-Shot Segmentationcited by 21
  5. 2023SEGIC: Unleashing the Emergent Correspondence for In-Context Segmentationcited by 19
  6. 2024Eliminating Feature Ambiguity for Few-Shot Segmentationcited by 19
  7. 2023PanoVOS: Bridging Non-panoramic and Panoramic Views with Transformer for Video Segmentationcited by 18
  8. 2023Focus on Query: Adversarial Mining Transformer for Few-Shot Segmentationcited by 13
  9. 2024Explore In-Context Segmentation via Latent Diffusion Modelscited by 12
  10. 2023Not Just Learning from Others but Relying on Yourself: A New Perspective on Few-Shot Segmentation in Remote Sensingcited by 11
  11. 2025Unlocking the Power of SAM 2 for Few-Shot Segmentationcited by 11
  12. 2023Harmonizing Base and Novel Classes: A Class-Contrastive Approach for Generalized Few-Shot Segmentationcited by 8
9 more
  1. 2023UniAP: Towards Universal Animal Perception in Vision via Few-shot Learningcited by 7
  2. 2023A Language-Guided Benchmark for Weakly Supervised Open Vocabulary Semantic Segmentationcited by 3
  3. 2024Group-On: Boosting One-Shot Segmentation with Supportive Querycited by 3
  4. 2023Language-guided Few-shot Semantic Segmentationcited by 2
  5. 2025UINO-FSS: Unifying Representation Learning and Few-shot Segmentation via Hierarchical Distillation and Mamba-HyperCorrelationcited by 1
  6. 2023Background Clustering Pre-training for Few-shot Segmentationcited by 0
  7. 2024More than the Sum of Its Parts: Ensembling Backbone Networks for Few-Shot Segmentationcited by 0
  8. 2024NubbleDrop: A Simple Way to Improve Matching Strategy for Prompted One-Shot Segmentationcited by 0
  9. 2024Generative Model-Based Fusion for Improved Few-Shot Semantic Segmentation of Infrared Imagescited by 0