Research map / Detection and segmentation / CNN features
Direction-Aware Spatial Context Features for Shadow Detection
Xiaowei Hu, Lei Zhu, Chi-Wing Fu, Jing Qin, Pheng-Ann Heng
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 multi-scale direction-aware spatial context modules (ablation) | basic shadow detection network · SBU | BER: 6.55 -> 5.59 | Improved |
| add spatial context without direction-aware attention (ablation) | basic shadow detection network · SBU | BER: 6.55 -> 6.23 | Improved |
| add direction-aware attention to spatial context features (ablation) | basic+context network · SBU | BER: 6.23 -> 5.59 | Improved |
| use 2 recurrent-translation rounds instead of 1 (ablation) | DSC module · SBU | BER: 5.85 -> 5.59 | Improved |
| use 2 recurrent-translation rounds instead of 3 (ablation) | DSC module · SBU | BER: 5.85 -> 5.59 | Improved |
| share attention weights across recurrent-translation rounds (ablation) | DSC module · SBU | BER: 6.02 -> 5.59 | Improved |
| use DSC instead of SRM | shadow detection · SBU | accuracy: 0.96 -> 0.97 | Improved |
| use DSC instead of SRM | shadow detection · UCF | BER: 9.81 -> 8.10 | Improved |
Closest papers by meaning
- Direction-Aware Spatial Context Features for Shadow Detection and Removal (TPAMI 2019 · similarity 0.96)
- Bidirectional Feature Pyramid Network with Recurrent Attention Residual Modules for Shadow Detection (ECCV 2018 · similarity 0.91)
- Distraction-Aware Shadow Detection (CVPR 2019 · similarity 0.87)
- Large Scale Shadow Annotation and Detection Using Lazy Annotation and Stacked CNNs (TPAMI 2019 · similarity 0.86)
- SILT: Shadow-Aware Iterative Label Tuning for Learning to Detect Shadows from Noisy Labels (ICCV 2023 · similarity 0.86)
- ARGAN: Attentive Recurrent Generative Adversarial Network for Shadow Detection and Removal (ICCV 2019 · similarity 0.86)
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.
