Research map / Detection and segmentation / CNN features
Scene Parsing With Global Context Embedding
Wei-Chih Hung, Yi-Hsuan Tsai, Xiaohui Shen, Zhe Lin, Kalyan Sunkavalli, Xin Lu, Ming-Hsuan 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 global context feature encoding (ablation) | FCN-8s · ADE20K val | Mean IU: 29.39 -> 32.48 | Improved |
| add global prior encoding (ablation) | FCN-8s · ADE20K val | Mean IU: 29.39 -> 32.92 | Improved |
| add global context feature encoding (ablation) | DeepLab · ADE20K val | Mean IU: 33.94 -> 37.06 | Improved |
| add global prior encoding (ablation) | DeepLab · ADE20K val | Mean IU: 33.94 -> 37.46 | Improved |
| combine feature and prior encoding with joint training (ablation) | DeepLab · ADE20K val | Mean IU: 33.94 -> 38.37 | Improved |
| combine feature and prior instead of prior alone (ablation) | DeepLab + Prior · ADE20K val | Pixel accuracy: 77.94 -> 77.76 | Hurt |
| add feature and prior encoding | DeepLab · PASCAL Context val | Mean IU: 44.38 -> 46.52 | Improved |
| add feature and prior encoding | DeepLab · PASCAL Context val | Pixel accuracy: 71.57 -> 73.80 | Improved |
| use learned global context feature instead of VGG-16 fc7 for retrieval (ablation) | retrieval · ADE20K val scene retrieval (Kp=5) | F2 score: 0.2524 -> 0.5601 | Improved |
| vary Ka in affinity matrix construction (ablation) | global context network · ADE20K val retrieval | F2 score: 0.5527 -> 0.5601 | No clear effect |
| increase Kp from 1 to 5 retrieved images (ablation) | prior generation · ADE20K val retrieval | F2 score: 0.4420 -> 0.5601 | Improved |
| increase Kp from 5 to 10 retrieved images (ablation) | prior generation · ADE20K val retrieval | F2 score: 0.5601 -> 0.5228 | Hurt |
Closest papers by meaning
- Adaptive Context Network for Scene Parsing (ICCV 2019 · similarity 0.90)
- Video Scene Parsing With Predictive Feature Learning (ICCV 2017 · similarity 0.89)
- Interaction via Bi-Directional Graph of Semantic Region Affinity for Scene Parsing (ICCV 2021 · similarity 0.89)
- Pyramid Scene Parsing Network (CVPR 2017 · similarity 0.89)
- Perspective-Adaptive Convolutions for Scene Parsing (TPAMI 2019 · similarity 0.89)
- The Scene Language: Representing Scenes with Programs, Words, and Embeddings (CVPR 2025 · similarity 0.87)
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.
