Research map / Detection and segmentation / CNN features
Semantic Correlation Promoted Shape-Variant Context for Segmentation
Henghui Ding, Xudong Jiang, Bing Shuai, Ai Qun Liu, Gang Wang
Check 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 SVC to the baseline (ablation) | FCN-4s with ResNet-101 · PASCAL-Context | IoU: 42.7 -> 52.4 | Improved |
| add LD after SVC (ablation) | FCN-4s with ResNet-101 · PASCAL-Context | IoU: 52.4 -> 53.2 | Improved |
| add SVC to the baseline (ablation) | FCN-4s with ResNet-101 · COCO-Stuff | IoU: 31.5 -> 38.5 | Improved |
| add LD after SVC (ablation) | FCN-4s with ResNet-101 · COCO-Stuff | IoU: 38.5 -> 39.6 | Improved |
| replace SFC with SVC at the same kernel size (ablation) | FCN-4s with ResNet-101 · PASCAL-Context | IoU: 45.6 -> 48.5; 46.6 -> 49.4; 47.1 -> 51.2; 47.0 -> 52.1; 46.7 -> 52.4; 46.5 -> 52.3 | Improved |
| increase SFC kernel size from 0×0 to 15×15 (ablation) | FCN-4s with ResNet-101 · PASCAL-Context | IoU: 42.7 -> 47.1 | Improved |
| increase SFC kernel size from 15×15 to 27×27 (ablation) | FCN-4s with ResNet-101 · PASCAL-Context | IoU: 47.1 -> 46.5 | Hurt |
| increase SVC kernel size from 0×0 to 23×23 (ablation) | FCN-4s with ResNet-101 · PASCAL-Context | IoU: 42.7 -> 52.4 | Improved |
| increase SVC kernel size from 23×23 to 27×27 (ablation) | FCN-4s with ResNet-101 · PASCAL-Context | IoU: 52.4 -> 52.3 | Hurt |
| use semantic-correlation shape masks for context aggregation rather than fixed spatial context | SVCNet · COCO-Stuff | mean IoU: 36.2 -> 39.6 | Improved |
Closest papers by meaning
- Context Encoding for Semantic Segmentation (CVPR 2018 · similarity 0.88)
- Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation (CVPR 2016 · similarity 0.88)
- ShapeConv: Shape-Aware Convolutional Layer for Indoor RGB-D Semantic Segmentation (ICCV 2021 · similarity 0.88)
- Exploring Context with Deep Structured Models for Semantic Segmentation (TPAMI 2017 · similarity 0.88)
- Unsupervised Semantic Segmentation Through Depth-Guided Feature Correlation and Sampling (CVPR 2024 · similarity 0.87)
- Bridge the Points: Graph-based Few-shot Segment Anything Semantically (NeurIPS 2024 · 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.
