mlsanityData to 14 Oct 2026

MFNet: Multi-class Few-shot Segmentation Network with Pixel-wise Metric Learning

arXiv 2111.00232 ↗First posted 30 Oct 2021cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

In visual recognition tasks, few-shot learning requires the ability to learn object categories with few support examples. Its re-popularity in light of the deep learning development is mainly in image classification. This work focuses on few-shot semantic segmentation, which is still a largely unexplored field. A few recent advances are often restricted to single-class few-shot segmentation. In this paper, we first present a novel multi-way (class) encoding and decoding architecture which effectively fuses multi-scale query information and multi-class support information into one query-support embedding. Multi-class segmentation is directly decoded upon this embedding. For better feature fusion, a multi-level attention mechanism is proposed within the architecture, which includes the attention for support feature modulation and attention for multi-scale combination. Last, to enhance the embedding space learning, an additional pixel-wise metric learning module is introduced with triplet loss formulated on the pixel-level embedding of the input image. Extensive experiments on standard benchmarks PASCAL-5i and COCO-20i show clear benefits of our method over the state of the art in few-shot segmentation

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 54 of its 82 references that are in the map. First posted on arXiv 30 Oct 2021.

Builds on

54 of 82 references.

References · 54

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  5. 2017Mask R-CNNcited by 7,277
  6. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  7. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  8. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  9. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,849
  10. 2016Matching Networks for One Shot Learningcited by 2,255
  11. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,161
  12. 2021Segmenter: Transformer for Semantic Segmentationcited by 855
38 more
  1. 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
  2. 2017One-Shot Learning for Semantic Segmentationcited by 337
  3. 2017Relation Networks for Object Detectioncited by 305
  4. 2018Context Encoding for Semantic Segmentationcited by 290
  5. 2020Prior Guided Feature Enrichment Network for Few-Shot Segmentationcited by 271
  6. 2018Few-shot Object Detection via Feature Reweightingcited by 265
  7. 2020Causal Intervention for Weakly-Supervised Semantic Segmentationcited by 229
  8. 2019CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learningcited by 217
  9. 2021Adaptive Prototype Learning and Allocation for Few-Shot Segmentationcited by 207
  10. 2021Hypercorrelation Squeeze for Few-Shot Segmentationcited by 193
  11. 2020Prototype Mixture Models for Few-shot Semantic Segmentationcited by 190
  12. 2019Feature Weighting and Boosting for Few-Shot Segmentationcited by 189
  13. 2019Meta R-CNN : Towards General Solver for Instance-level Few-shot Learningcited by 182
  14. 2018Low-Shot Learning from Imaginary Datacited by 181
  15. 2015Attention to Scale: Scale-aware Semantic Image Segmentationcited by 169
  16. 2018SG-One: Similarity Guidance Network for One-Shot Semantic Segmentationcited by 169
  17. 2020Part-aware Prototype Network for Few-shot Semantic Segmentationcited by 162
  18. 2019Semi-Supervised Semantic Segmentation with High- and Low-level Consistencycited by 147
  19. 2021Few-Shot Segmentation via Cycle-Consistent Transformercited by 133
  20. 2021Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformercited by 116
  21. 2020CRNet: Cross-Reference Networks for Few-Shot Segmentationcited by 101
  22. 2021Self-Guided and Cross-Guided Learning for Few-Shot Segmentationcited by 92
  23. 2018RepMet: Representative-based metric learning for classification and one-shot object detectioncited by 85
  24. 2019Hierarchical Clustering with Hard-batch Triplet Loss for Person Re-identificationcited by 83
  25. 2018Blazingly Fast Video Object Segmentation with Pixel-Wise Metric Learningcited by 74
  26. 2021Mining Latent Classes for Few-shot Segmentationcited by 69
  27. 2020HyperSeg: Patch-wise Hypernetwork for Real-time Semantic Segmentationcited by 66
  28. 2019Dense Classification and Implanting for Few-Shot Learningcited by 56
  29. 2021Learning Meta-class Memory for Few-Shot Semantic Segmentationcited by 56
  30. 2018Learning Compositional Representations for Few-Shot Recognitioncited by 50
  31. 2015Semantic Image Segmentation via Deep Parsing Networkcited by 44
  32. 2020On the Texture Bias for Few-Shot CNN Segmentationcited by 38
  33. 2018Weakly Supervised Scene Parsing with Point-based Distance Metric Learningcited by 33
  34. 2019Differentiable Meta-learning Model for Few-shot Semantic Segmentationcited by 31
  35. 2020BriNet: Towards Bridging the Intra-class and Inter-class Gaps in One-Shot Segmentationcited by 28
  36. 2020Restoring Negative Information in Few-Shot Object Detectioncited by 28
  37. 2021Anti-aliasing Semantic Reconstruction for Few-Shot Semantic Segmentationcited by 23
  38. 2019Revisiting Metric Learning for Few-Shot Image Classificationcited by 14

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 6; 2025: 3; 2026: 1.

10 papers.

  1. 2024Rethinking Prior Information Generation with CLIP for Few-Shot Segmentationcited by 20
  2. 2024Label Anything: Multi-Class Few-Shot Semantic Segmentation with Visual Promptscited by 9
  3. 2026Revealing the Semantic Selection Gap in DINOv3 through Training-Free Few-Shot Segmentationcited by 3
  4. 2024Weighting Pseudo-Labels via High-Activation Feature Index Similarity and Object Detection for Semi-Supervised Segmentationcited by 2
  5. 2024Enhancing Generalized Few-Shot Semantic Segmentation via Effective Knowledge Transfercited by 2
  6. 2025Balancing Conservatism and Aggressiveness: Prototype-Affinity Hybrid Network for Few-Shot Segmentationcited by 1
  7. 2025Take a Peek: Efficient Encoder Adaptation for Few-Shot Semantic Segmentation via LoRAcited by 1
  8. 2024Boosting Few-Shot Segmentation via Instance-Aware Data Augmentation and Local Consensus Guided Cross Attentioncited by 0
  9. 2024Memory-guided Network with Uncertainty-based Feature Augmentation for Few-shot Semantic Segmentationcited by 0
  10. 2025Efficient Masked Attention Transformer for Few-Shot Classification and Segmentationcited by 0