Research map / Detection and segmentation / Open-set and few-shot detection
Prototype Mixture Models for Few-shot Semantic Segmentation
Boyu Yang, Chang Liu, Bohao Li, Jianbin Jiao, Qixiang Ye
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| replace global-average prototype with PMMs (P-Match) (ablation) | CANet baseline · Pascal-5i mean | mIoU: 51.93 -> 54.63 | Improved |
| add duplex P-Conv with background prototypes (ablation) | PMMs+ · Pascal-5i mean | mIoU: 54.63 -> 55.27 | Improved |
| stack residual PMMs (RPMMs) (ablation) | PMMs · Pascal-5i mean | mIoU: 55.27 -> 56.34 | Improved |
| use 2 prototypes instead of 1 (ablation) | PMMs+ · Pascal-5i mean | mIoU: 53.69 -> 54.41 | Improved |
| increase prototypes from 3 to 5 (ablation) | PMMs+ · Pascal-5i mean | mIoU: 54.63 -> 54.09 | Hurt |
| use VMF kernel instead of Gaussian (ablation) | PMMs+ · Pascal-5i mean | mIoU: 54.04 -> 54.63 | Improved |
| use RPMMs over CANet (ResNet50) | RPMMs · Pascal-5i 1-shot | mean mIoU: 53.96 -> 56.34 | Improved |
| use RPMMs over CANet (ResNet50) | RPMMs · Pascal-5i 5-shot | mean mIoU: 55.80 -> 57.30 | Improved |
| use RPMMs over baseline | RPMMs · COCO-20i 1-shot | mean mIoU: 26.11 -> 30.58 | Improved |
| use RPMMs over baseline | RPMMs · COCO-20i 5-shot | mean mIoU: 27.86 -> 35.52 | Improved |
| add stacked residual branch (ablation) | PMMs · COCO-20i 1-shot | mean mIoU: 29.61 -> 30.58 | Improved |
| add stacked residual branch (ablation) | PMMs · Pascal-5i 1-shot | Pascal-5^3 mIoU: 49.81 -> 50.68 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- PANet — PANet: Few-Shot Image Semantic Segmentation With Prototype Alignment (ICCV 2019) · better on 4 of 4 shared results
- CANet — CANet: Class-Agnostic Segmentation Networks With Iterative Refinement and Attentive Few-Shot Learning (CVPR 2019) · better on 2 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Learning from the Target: Dual Prototype Network for Few Shot Semantic Segmentation (AAAI 2022 · similarity 0.90)
- Part-aware Prototype Network for Few-shot Semantic Segmentation (ECCV 2020 · similarity 0.90)
- CGMGM: A Cross-Gaussian Mixture Generative Model for Few-Shot Semantic Segmentation (AAAI 2024 · similarity 0.90)
- DSV-LFS: Unifying LLM-Driven Semantic Cues with Visual Features for Robust Few-Shot Segmentation (CVPR 2025 · similarity 0.88)
- Unlocking the Potential of Pre-trained Vision Transformers for Few-Shot Semantic Segmentation through Relationship Descriptors (CVPR 2024 · similarity 0.88)
- A Surprisingly Simple Approach to Generalized Few-Shot Semantic Segmentation (NeurIPS 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
