Research map / Detection and segmentation / Open-set and few-shot detection
Prototypical Kernel Learning and Open-set Foreground Perception for Generalized Few-shot Semantic Segmentation
Kai Huang, Feigege Wang, Ye Xi, Yutao Gao
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 prototypical kernel learning (PKL) to the baseline (ablation) | GFSS kernel baseline · PASCAL-5i 1-shot | hIoU: 23.45 -> 34.17 | Improved |
| add foreground contextual perception (FCP) to the baseline (ablation) | GFSS kernel baseline · PASCAL-5i 1-shot | hIoU: 23.45 -> 26.57 | Improved |
| add conditional bias based inference (CBBI) on top of PKL+FCP (ablation) | Ours · PASCAL-5i 1-shot | hIoU: 34.98 -> 37.83 | Improved |
| add CBBI on top of PKL+FCP (ablation) | Ours · PASCAL-5i 5-shot | hIoU: 43.02 -> 45.42 | Improved |
| use adaptive learning rate (cosine similarity with ReLU) instead of fixed rate in kernel update (ablation) | PKL · PASCAL-5i 1-shot | hIoU: 31.36 -> 37.83 | Improved |
| use prototypical kernel update instead of concat plus linear projection or adaptive pooling fusion (ablation) | PKL · PASCAL-5i 1-shot | hIoU: 32.11 -> 37.83 (vs concat+LP) | Improved |
| use max pooling over pixels and average pooling over images in FCP hybrid pooling (ablation) | FCP · PASCAL-5i 1-shot | hIoU: 33.34 -> 37.83 (pixel avg pooling variant) | Improved |
| use FCP instead of salient detectors PAGENet or MINet for foreground (ablation) | Ours · PASCAL-5i 1-shot | hIoU: 36.28 -> 37.83 (vs PAGENet); 36.53 (MINet) | Improved |
| use GradCAM as foreground module instead of FCP (ablation) | Ours · PASCAL-5i 1-shot | hIoU: 37.83 -> 34.74 | Hurt |
| use unconditional or learnable-convolution fusion instead of conditional bias inference (ablation) | Ours · PASCAL-5i 1-shot | hIoU: uCBBI 31.70, cCBBI 29.29 vs 37.83; both below no CBBI (34.98) | Hurt |
| increase the number of COCO classes (15 to 60 base classes) (ablation) | Ours versus CAPL · COCO subset, novel mIoU gain over CAPL | mIoU novel improvement: +7.76 -> +3.99 | Hurt |
| replace CAPL with the proposed method in GFSS on PASCAL-5i | GFSS PASCAL-5i · PASCAL-5i 5-shot | hIoU: 31.96 -> 45.42 | Improved |
Closest papers by meaning
- A Surprisingly Simple Approach to Generalized Few-Shot Semantic Segmentation (NeurIPS 2024 · similarity 0.93)
- Enhancing Generalized Few-Shot Semantic Segmentation via Effective Knowledge Transfer (AAAI 2025 · similarity 0.91)
- Label-Efficient Few-Shot Semantic Segmentation with Unsupervised Meta-Training (AAAI 2024 · similarity 0.89)
- Unlocking the Potential of Pre-trained Vision Transformers for Few-Shot Semantic Segmentation through Relationship Descriptors (CVPR 2024 · similarity 0.89)
- DSV-LFS: Unifying LLM-Driven Semantic Cues with Visual Features for Robust Few-Shot Segmentation (CVPR 2025 · similarity 0.88)
- Few-Shot Incremental Learning via Foreground Aggregation and Knowledge Transfer for Audio-Visual Semantic Segmentation (AAAI 2025 · similarity 0.88)
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.
