Research map / Detection and segmentation / Open-set and few-shot detection
Consistent Structural Relation Learning for Zero-Shot Segmentation
Peike Li, Yunchao Wei, Yi Yang
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 pair-wise relation consistency to point-wise only (ablation) | CSRL · Pascal-VOC unseen-2 | hIoU: 51.9% -> 54.5% | Improved |
| add list-wise relation consistency to point-wise only (ablation) | CSRL · Pascal-VOC unseen-2 | hIoU: 51.9% -> 53.9% | Improved |
| add both pair-wise and list-wise to point-wise (ablation) | CSRL · Pascal-VOC unseen-2 | hIoU: 51.9% -> 56.3% | Improved |
| add pair-wise consistency (ablation) | CSRL · Pascal-VOC unseen-2 | unseen mIoU: 40.3% -> 43.3% | Improved |
| add list-wise consistency (ablation) | CSRL · Pascal-VOC unseen-2 | unseen mIoU: 40.3% -> 42.7% | Improved |
| structural relation generator vs ZS3Net generator | CSRL · Pascal-VOC unseen-2 | hIoU: 47.5% -> 56.3% | Improved |
| structural relation generator vs ZS3Net generator | CSRL · Pascal-VOC unseen-10 | hIoU: 23.6% -> 31.0% | Improved |
| structural relation generator vs ZS3Net generator | CSRL · Pascal-Context unseen-4 | unseen mIoU: 24.9% -> 23.9% | Mixed |
| structural relation generator vs ZS3Net generator | CSRL · Pascal-Context unseen-2 | hIoU: 28.4% -> 33.4% | Improved |
Closest papers by meaning
- Primitive Generation and Semantic-Related Alignment for Universal Zero-Shot Segmentation (CVPR 2023 · similarity 0.92)
- Exploiting a Joint Embedding Space for Generalized Zero-Shot Semantic Segmentation (ICCV 2021 · similarity 0.91)
- VGSE: Visually-Grounded Semantic Embeddings for Zero-Shot Learning (CVPR 2022 · similarity 0.91)
- Zero-Shot Semantic Segmentation (NeurIPS 2019 · similarity 0.91)
- ZeroDiff: Solidified Visual-semantic Correlation in Zero-Shot Learning (ICLR 2025 · similarity 0.88)
- Relationship Prompt Learning is Enough for Open-Vocabulary Semantic Segmentation (NeurIPS 2024 · 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.
