Research map / Detection and segmentation / Open-set and few-shot detection
Prior Guided Feature Enrichment Network for Few-Shot Segmentation
Zhuotao Tian, Hengshuang Zhao, Michelle Shu, Zhicheng Yang, Ruiyu Li, Jiaya Jia
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 |
|---|---|---|---|
| add top-down inter-scale path to FEM (ablation) | PFENet FEM · PASCAL-5i 1-shot | mean class mIoU: 59.8 -> 60.8 | Improved |
| use bottom-up instead of top-down path (ablation) | PFENet FEM · PASCAL-5i 5-shot | mean class mIoU: 61.9 -> 60.7 | Hurt |
| add bidirectional TD+BU path instead of TD (ablation) | PFENet FEM · PASCAL-5i 5-shot | mean class mIoU: 61.9 -> 62.0 | No clear effect |
| replace FEM with PPM (ablation) | Baseline · PASCAL-5i 1-shot | mean class mIoU: 59.2 -> 57.1 | Hurt |
| add FEM with scales {60,30,15,8} to baseline (ablation) | Baseline · PASCAL-5i 1-shot | mean class mIoU: 56.3 -> 59.2 | Improved |
| add extra scale 4 to FEM (more parameters) (ablation) | FEM · PASCAL-5i 1-shot | mean class mIoU: 59.2 -> 58.9 | Hurt |
| add prior mask from fixed high-level features (ablation) | Baseline + FEM · PASCAL-5i 1-shot | mean class mIoU: 59.2 -> 60.8 | Improved |
| generate prior from learnable high-level features instead of fixed (ablation) | VGG-16 baseline · PASCAL-5i 1-shot | mean class mIoU: 53.3 -> 48.9 | Hurt |
| add prior from fixed high-level features (ablation) | VGG-16 baseline · PASCAL-5i 1-shot | mean class mIoU: 53.3 -> 55.4 | Improved |
| use average similarity instead of max for prior (ablation) | Prior_FH · PASCAL-5i 1-shot | mean class mIoU: 55.4 -> 55.1 | Hurt |
| use mask-pooled support feature for prior (ablation) | Prior_FH · PASCAL-5i 1-shot | mean class mIoU: 55.4 -> 54.7 | Hurt |
| add prior mask on totally unseen FSS-1000 classes | Baseline · FSS-1000 unseen classes | foreground IoU: 79.7 -> 80.8 | Improved |
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 5 of 5 shared results
- CANet — CANet: Class-Agnostic Segmentation Networks With Iterative Refinement and Attentive Few-Shot Learning (CVPR 2019) · better on 2 of 2 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
- Relevant Intrinsic Feature Enhancement Network for Few-Shot Semantic Segmentation (AAAI 2024 · similarity 0.89)
- A Surprisingly Simple Approach to Generalized Few-Shot Semantic Segmentation (NeurIPS 2024 · similarity 0.88)
- Rethinking Prior Information Generation with CLIP for Few-Shot Segmentation (CVPR 2024 · similarity 0.88)
- Unlocking the Potential of Pre-trained Vision Transformers for Few-Shot Semantic Segmentation through Relationship Descriptors (CVPR 2024 · similarity 0.87)
- APSeg: Auto-Prompt Network for Cross-Domain Few-Shot Semantic Segmentation (CVPR 2024 · similarity 0.87)
- Unleashing the Potential of the Diffusion Model in 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.
