Research map / Detection and segmentation / CNN features
Single-Stage Instance Shadow Detection With Bidirectional Relation Learning
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 LISA with single-stage SSIS | Instance shadow detection · SOBA test | SOAPsegm: 21.2 -> 27.4 | Helped |
| Replace LISA with single-stage SSIS | Instance shadow detection · SOBA test | SOAPbbox: 21.7 -> 25.5 | Helped |
| Replace LISA with single-stage SSIS | Instance shadow detection · SOBA test | Association APsegm: 40.8 -> 50.5 | Helped |
| Replace LISA with single-stage SSIS | Instance shadow detection · SOBA test | Instance APsegm: 37.0 -> 40.3 | Helped |
| Add offset vectors to the basic network (ablation) | SSIS · SOBA test | Association APsegm: 47.4 -> 48.9 | Helped |
| Add offset vectors to the basic network (ablation) | SSIS · SOBA test | Association APbbox: 53.7 -> 55.5 | Helped |
| Add offset vectors to the basic network (ablation) | SSIS · SOBA test | SOAPsegm: 25.5 -> 25.4 | Hurt |
| Add class vectors to offset-based relation learning (ablation) | SSIS · SOBA test | SOAPsegm: 25.4 -> 27.4 | Helped |
| Add class vectors to offset-based relation learning (ablation) | SSIS · SOBA test | Instance APsegm: 39.3 -> 40.3 | Helped |
| Use bidirectional rather than object-to-shadow-only learning (ablation) | SSIS · SOBA test | SOAPsegm: 20.8 -> 27.4 | Helped |
| Use bidirectional rather than shadow-to-object-only learning (ablation) | SSIS · SOBA test | SOAPsegm: 23.9 -> 27.4 | Helped |
| Use the proposed inference strategy instead of directly combining main and associated branch masks (ablation) | SSIS · SOBA test | SOAPsegm: 21.1 -> 27.4 | Helped |
Closest papers by meaning
- Instance Shadow Detection (CVPR 2020 · similarity 0.90)
- Efficient Model-Driven Network for Shadow Removal (AAAI 2022 · similarity 0.87)
- A Multi-Task Mean Teacher for Semi-Supervised Shadow Detection (CVPR 2020 · similarity 0.86)
- OmniSR: Shadow Removal Under Direct and Indirect Lighting (AAAI 2025 · similarity 0.83)
- DeS3: Adaptive Attention-Driven Self and Soft Shadow Removal Using ViT Similarity (AAAI 2024 · similarity 0.83)
- Shadow-Enlightened Image Outpainting (CVPR 2024 · similarity 0.83)
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.