mlsanityData to 7 Oct 2026

Mask Matching Transformer for Few-Shot Segmentation

arXiv 2301.01208 ↗First posted 5 Dec 2022cs.CVcited by 22

Not on the map. Why?

Abstract (arXiv)

In this paper, we aim to tackle the challenging few-shot segmentation task from a new perspective. Typical methods follow the paradigm to firstly learn prototypical features from support images and then match query features in pixel-level to obtain segmentation results. However, to obtain satisfactory segments, such a paradigm needs to couple the learning of the matching operations with heavy segmentation modules, limiting the flexibility of design and increasing the learning complexity. To alleviate this issue, we propose Mask Matching Transformer (MM-Former), a new paradigm for the few-shot segmentation task. Specifically, MM-Former first uses a class-agnostic segmenter to decompose the query image into multiple segment proposals. Then, a simple matching mechanism is applied to merge the related segment proposals into the final mask guided by the support images. The advantages of our MM-Former are two-fold. First, the MM-Former follows the paradigm of decompose first and then blend, allowing our method to benefit from the advanced potential objects segmenter to produce high-quality mask proposals for query images. Second, the mission of prototypical features is relaxed to learn coefficients to fuse correct ones within a proposal pool, making the MM-Former be well generalized to complex scenarios or cases. We conduct extensive experiments on the popular COCO-20i and Pascal-5i benchmarks. Competitive results well demonstrate the effectiveness and the generalization ability of our MM-Former.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 32 of its 52 references that are in the map. First posted on arXiv 5 Dec 2022.

Builds on

32 of 52 references.

References · 32

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2020End-to-End Object Detection with Transformerscited by 7,384
  6. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  7. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  8. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  9. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,923
  10. 2016Pyramid Scene Parsing Networkcited by 2,472
  11. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,338
  12. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,148
20 more
  1. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  2. 2018CCNet: Criss-Cross Attention for Semantic Segmentationcited by 717
  3. 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
  4. 2017One-Shot Learning for Semantic Segmentationcited by 337
  5. 2020Prior Guided Feature Enrichment Network for Few-Shot Segmentationcited by 271
  6. 2019CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learningcited by 217
  7. 2021Adaptive Prototype Learning and Allocation for Few-Shot Segmentationcited by 207
  8. 2021Hypercorrelation Squeeze for Few-Shot Segmentationcited by 193
  9. 2020Prototype Mixture Models for Few-shot Semantic Segmentationcited by 190
  10. 2019Feature Weighting and Boosting for Few-Shot Segmentationcited by 189
  11. 2018SG-One: Similarity Guidance Network for One-Shot Semantic Segmentationcited by 169
  12. 2014Simultaneous Detection and Segmentationcited by 158
  13. 2020Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?cited by 135
  14. 2021Few-Shot Segmentation via Cycle-Consistent Transformercited by 133
  15. 2021Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformercited by 116
  16. 2021Self-Guided and Cross-Guided Learning for Few-Shot Segmentationcited by 92
  17. 2016Learning Dense Correspondence via 3D-guided Cycle Consistencycited by 91
  18. 2021Learning Meta-class Memory for Few-Shot Semantic Segmentationcited by 56
  19. 2021Polarized Self-Attention: Towards High-quality Pixel-wise Regressioncited by 39
  20. 2021Anti-aliasing Semantic Reconstruction for Few-Shot Semantic Segmentationcited by 23

Built on by

Cited by year (2026 to 7 Oct)

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

22 papers.

Sort:

By area:

  1. 2023Transformer-Based Visual Segmentation: A Surveycited by 124
  2. 2023Learning Mask-aware CLIP Representations for Zero-Shot Segmentationcited by 57
  3. 2023LLaFS: When Large Language Models Meet Few-Shot Segmentationcited by 48
  4. 2024Bridge the Points: Graph-based Few-shot Segment Anything Semanticallycited by 35
  5. 2023Self-Calibrated Cross Attention Network for Few-Shot Segmentationcited by 32
  6. 2024Hybrid Mamba for Few-Shot Segmentationcited by 21
  7. 2024Eliminating Feature Ambiguity for Few-Shot Segmentationcited by 19
  8. 2023Focus on Query: Adversarial Mining Transformer for Few-Shot Segmentationcited by 13
  9. 2023Partition-A-Medical-Image: Extracting Multiple Representative Sub-regions for Few-shot Medical Image Segmentationcited by 9
  10. 2024RobustEMD: Domain Robust Matching for Cross-domain Few-shot Medical Image Segmentationcited by 6
  11. 2025DSV-LFS: Unifying LLM-Driven Semantic Cues with Visual Features for Robust Few-Shot Segmentationcited by 6
  12. 2023Dense Affinity Matching for Few-Shot Segmentationcited by 5
10 more
  1. 2025Deep Skin Lesion Segmentation with Transformer-CNN Fusion: Toward Intelligent Skin Cancer Analysiscited by 5
  2. 2025Controlling Latent Diffusion Using Latent CLIPcited by 4
  3. 2024Beyond Mask: Rethinking Guidance Types in Few-shot Segmentationcited by 3
  4. 2025RAU: Reference-based Anatomical Understanding with Vision Language Modelscited by 3
  5. 2025ProMi: An Efficient Prototype-Mixture Baseline for Few-Shot Segmentation with Bounding-Box Annotationscited by 1
  6. 2025Balancing Conservatism and Aggressiveness: Prototype-Affinity Hybrid Network for Few-Shot Segmentationcited by 1
  7. 2024Memory-guided Network with Uncertainty-based Feature Augmentation for Few-shot Semantic Segmentationcited by 0
  8. 2024Improving 3D Few-Shot Segmentation with Inference-Time Pseudo-Labelingcited by 0
  9. 2025Beyond Visual Cues: Leveraging General Semantics as Support for Few-Shot Segmentationcited by 0
  10. 2026Exploiting Target Knowledge from MLLMs for Robust Few-Shot Segmentationcited by 0