Data to 14 Oct 2026

Prototype Mixture Models for Few-shot Semantic Segmentation

arXiv 2008.03898 ↗First posted 10 Aug 2020cs.CVcited by 190

Not on the map. Why?

Abstract (arXiv)

Few-shot segmentation is challenging because objects within the support and query images could significantly differ in appearance and pose. Using a single prototype acquired directly from the support image to segment the query image causes semantic ambiguity. In this paper, we propose prototype mixture models (PMMs), which correlate diverse image regions with multiple prototypes to enforce the prototype-based semantic representation. Estimated by an Expectation-Maximization algorithm, PMMs incorporate rich channel-wised and spatial semantics from limited support images. Utilized as representations as well as classifiers, PMMs fully leverage the semantics to activate objects in the query image while depressing background regions in a duplex manner. Extensive experiments on Pascal VOC and MS-COCO datasets show that PMMs significantly improve upon state-of-the-arts. Particularly, PMMs improve 5-shot segmentation performance on MS-COCO by up to 5.82% with only a moderate cost for model size and inference speed.

Key facts. Cited by 190 papers in the map (data through 14 Oct 2026). First posted on arXiv 10 Aug 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 39; 2022: 44; 2023: 42; 2024: 34; 2025: 23; 2026: 8.

190 papers.

Sort:

By area:

2021Image Segmentation Using Text and Image Promptscited by 512
2022Visual Prompting via Image Inpaintingcited by 250
2021Adaptive Prototype Learning and Allocation for Few-Shot Segmentationcited by 207
2021Hypercorrelation Squeeze for Few-Shot Segmentationcited by 193
2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 163
2021Few-Shot Segmentation via Cycle-Consistent Transformercited by 133
2022Learning What Not to Segment: A New Perspective on Few-Shot Segmentationcited by 120
2021Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformercited by 116
2022Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentationcited by 114
2022Self-Support Few-Shot Semantic Segmentationcited by 96
2021Self-Guided and Cross-Guided Learning for Few-Shot Segmentationcited by 92
2023Hierarchical Dense Correlation Distillation for Few-Shot Segmentationcited by 84

38 more

2022FS6D: Few-Shot 6D Pose Estimation of Novel Objectscited by 81
2021Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detectioncited by 80
2024VRP-SAM: SAM with Visual Reference Promptcited by 75
2021Mining Latent Classes for Few-shot Segmentationcited by 69
2022Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentationcited by 65
2022Feature-Proxy Transformer for Few-Shot Segmentationcited by 58
2022Learning Non-target Knowledge for Few-shot Semantic Segmentationcited by 57
2021Learning Meta-class Memory for Few-Shot Semantic Segmentationcited by 56
2022Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuningcited by 50
2021Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentationcited by 43
2022Dynamic Prototype Convolution Network for Few-Shot Semantic Segmentationcited by 43
2022Open-vocabulary Semantic Segmentation with Frozen Vision-Language Modelscited by 39
2022Intermediate Prototype Mining Transformer for Few-Shot Semantic Segmentationcited by 37
2021Few-shot Segmentation with Optimal Transport Matching and Message Flowcited by 36
2021PFENet++: Boosting Few-shot Semantic Segmentation with the Noise-filtered Context-aware Prior Maskcited by 31
2022Unsupervised Video Object Segmentation via Prototype Memory Networkcited by 30
2024Cross-Domain Few-Shot Segmentation via Iterative Support-Query Correspondence Miningcited by 30
2024Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognitioncited by 29
2023Prototype Adaption and Projection for Few- and Zero-shot 3D Point Cloud Semantic Segmentationcited by 26
2024APSeg: Auto-Prompt Network for Cross-Domain Few-Shot Semantic Segmentationcited by 26
2021All-Around Real Label Supervision: Cyclic Prototype Consistency Learning for Semi-supervised Medical Image Segmentationcited by 25
2022Integrative Few-Shot Learning for Classification and Segmentationcited by 25
2022Interclass Prototype Relation for Few-Shot Segmentationcited by 25
2023Distilling Self-Supervised Vision Transformers for Weakly-Supervised Few-Shot Classification & Segmentationcited by 24
2021Anti-aliasing Semantic Reconstruction for Few-Shot Semantic Segmentationcited by 23
2022Doubly Deformable Aggregation of Covariance Matrices for Few-shot Segmentationcited by 23
2022A Strong Baseline for Generalized Few-Shot Semantic Segmentationcited by 22
2022Mask Matching Transformer for Few-Shot Segmentationcited by 22
2023FECANet: Boosting Few-Shot Semantic Segmentation with Feature-Enhanced Context-Aware Networkcited by 22
2023DifFSS: Diffusion Model for Few-Shot Semantic Segmentationcited by 22
2023UniRef++: Segment Every Reference Object in Spatial and Temporal Spacescited by 22
2024Adapt Before Comparison: A New Perspective on Cross-Domain Few-Shot Segmentationcited by 22
2022CREAM: Weakly Supervised Object Localization via Class RE-Activation Mappingcited by 21
2022MSANet: Multi-Similarity and Attention Guidance for Boosting Few-Shot Segmentationcited by 21
2023Learning Expressive Prompting With Residuals for Vision Transformerscited by 21
2023Visual and Textual Prior Guided Mask Assemble for Few-Shot Segmentation and Beyondcited by 19
2022MSI: Maximize Support-Set Information for Few-Shot Segmentationcited by 18
2023CoinSeg: Contrast Inter- and Intra- Class Representations for Incremental Segmentationcited by 18

50 most cited of 190 All 190 (JSON)