Research map / Detection and segmentation / CNN features
Towards Bridging Semantic Gap to Improve Semantic Segmentation
Yanwei Pang, Yazhao Li, Jianbing Shen, Ling Shao
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 parallel feature pyramid (PFP) without SeEM (ablation) | ResNet50 baseline · PASCAL VOC 2012 val | mIoU: 70.9 -> 72.7 | Improved |
| add PFP without SeEM (ablation) | ResNet101 baseline · PASCAL VOC 2012 val | mIoU: 74.9 -> 75.7 | Improved |
| embed three SeEM modules in PFP (ablation) | PFP with ResNet101 · PASCAL VOC 2012 val | mIoU: 75.7 -> 76.9 | Improved |
| add a single SeEM-FS module to the baseline (ablation) | ResNet101 baseline · PASCAL VOC 2012 val | mIoU: 74.9 -> 75.9 | Improved |
| embed three SeEM-FS modules instead of SeEM in PFP (ablation) | PFP with ResNet101 · PASCAL VOC 2012 val | mIoU: 76.9 -> 77.5 | Improved |
| add boundary refinement by skip connection (ablation) | PFPc · PASCAL VOC 2012 val | mIoU: 77.4 -> 77.7 | Improved |
| use boundary attention module (BAM) instead of skip connection (ablation) | PFPc · PASCAL VOC 2012 val | mIoU: 77.4 -> 78.1 | Improved |
| enhance Block2 features with SeEM before prediction (ablation) | SeENet features · PASCAL VOC 2012 val | mIoU: 50.1 -> 62.4 | Improved |
| combine Block3 with SeEM-enhanced Block2 instead of raw Block2 (ablation) | SeENet features · PASCAL VOC 2012 val | mIoU: 71.5 -> 73.5 | Improved |
| use BAM instead of no boundary refinement, 1 pixel trimap (ablation) | SeENet · PASCAL VOC 2012 val | boundary mIoU: 50.5 -> 56.1 | Improved |
| increase training crop size from 320 to 512 | SeENet · PASCAL VOC 2012 test | mIoU: +1.3% | Improved |
| add COCO pre-training and multi-scale testing | SeENet · PASCAL VOC 2012 test | mIoU: 83.8 -> 86.6 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- PSANet — PSANet: Point-wise Spatial Attention Network for Scene Parsing (ECCV 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
- Multi-Scale Context Intertwining for Semantic Segmentation (ECCV 2018 · similarity 0.89)
- ExFuse: Enhancing Feature Fusion for Semantic Segmentation (ECCV 2018 · similarity 0.89)
- Gated Fully Fusion for Semantic Segmentation (AAAI 2020 · similarity 0.88)
- ISNet: Integrate Image-Level and Semantic-Level Context for Semantic Segmentation (ICCV 2021 · similarity 0.88)
- Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation (CVPR 2016 · similarity 0.88)
- Unsupervised Semantic Segmentation Through Depth-Guided Feature Correlation and Sampling (CVPR 2024 · 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.
