Research map / Detection and segmentation / CNN features
Large-Field Contextual Feature Learning for Glass Detection
Haiyang Mei, Xin She Yang, Letian Yu, Qiang Zhang, Xiaopeng Wei, Rynson W. H. Lau
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 LCFI module to base network (ablation) | GDNet base · GDD | IoU: 84.89 -> 87.63 | Improved |
| add LCFI module to base network (ablation) | GDNet base · GDD | BER: 7.40 -> 5.62 | Improved |
| increase LCFI from one scale to two scales (ablation) | LCFI · GDD | IoU: 86.22 -> 86.78 | Improved |
| increase LCFI from two scales to four scales (ablation) | LCFI · GDD | IoU: 86.78 -> 87.63 | Improved |
| use dilated convolutions instead of local convolutions in LCFI (ablation) | LCFI · GDD | IoU: 86.93 -> 87.13 | Improved |
| use spatially separable convolutions instead of dilated convolutions (ablation) | LCFI · GDD | IoU: 87.13 -> 87.31 | Improved |
| add a second parallel spatially separable path in each LCFI block (ablation) | LCFI · GDD | IoU: 87.31 -> 87.63 | Improved |
| add boundary feature enhancement (BFE) module (ablation) | GDNet · GDD | IoU: 87.63 -> 87.83 | Improved |
| add boundary feature enhancement (BFE) module (ablation) | GDNet · GDD | BER: 5.62 -> 5.52 | Improved |
| use ResNeXt-101 instead of ResNet-101 backbone (ablation) | GDNet-B · GDD | IoU: 86.84 -> 87.83 | Improved |
| use SENet-154 instead of ResNeXt-101 backbone (ablation) | GDNet-B · GDD | IoU: 87.83 -> 88.09 | Improved |
| use GDNet-B over best prior MirrorNet on mirror segmentation | MirrorNet · MSD | IoU: 78.95 -> 81.70 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 on most shared results.
- CCNet — CCNet: Criss-Cross Attention for Semantic Segmentation (ICCV 2019) · better on 2 of 2 shared results
- EGNet — EGNet: Edge Guidance Network for Salient Object Detection (ICCV 2019) · better on 2 of 2 shared results
- DANet — DANet: Divergent Activation for Weakly Supervised Object Localization (ICCV 2019) · better on 1 of 1 shared result
- PiCANet — PiCANet: Learning Pixel-Wise Contextual Attention for Saliency Detection (CVPR 2018) · better on 1 of 1 shared result
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
- Don't Hit Me! Glass Detection in Real-World Scenes (CVPR 2020 · similarity 0.96)
- Rich Context Aggregation With Reflection Prior for Glass Surface Detection (CVPR 2021 · similarity 0.92)
- Exploiting Semantic Relations for Glass Surface Detection (NeurIPS 2022 · similarity 0.92)
- Leveraging RGB-D Data with Cross-Modal Context Mining for Glass Surface Detection (AAAI 2025 · similarity 0.90)
- Multi-View Dynamic Reflection Prior for Video Glass Surface Detection (AAAI 2024 · similarity 0.89)
- SAFDNet: A Simple and Effective Network for Fully Sparse 3D Object Detection (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.
