Research map / Detection and segmentation / CNN features
Fully Attentional Network for Semantic Segmentation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 a fully attentional block instead of channel-only attention (ablation) | ResNet50 segmentation baseline · Cityscapes validation | mIoU (SS): 75.6 -> 78.9 | Helped |
| Add a fully attentional block instead of spatial-only attention (ablation) | ResNet50 segmentation baseline · Cityscapes validation | mIoU (SS): 76.3 -> 78.9 | Helped |
| Use one fully attentional block instead of sequential or dual channel-spatial NL blocks (ablation) | ResNet50 segmentation baseline · Cityscapes validation | mIoU (SS): 77.1 -> 78.9; 77.4 -> 78.9 | Helped |
| Add FLA (ablation) | ShuffleNetV2 segmentation baseline · Cityscapes validation | mIoU (SS): 69.2 -> 74.7 | Helped |
| Add FLA (ablation) | ResNet18 segmentation baseline · Cityscapes validation | mIoU (SS): 71.3 -> 76.5 | Helped |
| Add FLA (ablation) | ResNet50 segmentation baseline · Cityscapes validation | mIoU (MS+F): 75.8 -> 79.7 | Helped |
| Add FLA (ablation) | ResNet101 segmentation baseline · Cityscapes validation | mIoU (MS+F): 76.9 -> 82.6 | Helped |
| Use FLANet rather than the strongest listed ResNet101 baseline | ResNet101 segmentation · Cityscapes test | mIoU: 82.4 -> 83.0 | Helped |
| Use FLANet rather than the strongest listed ResNet101 baseline | ResNet101 segmentation · ADE20K validation | mIoU: 46.27 -> 46.68 | Helped |
| Use FLANet with ResNet150 rather than RecoNet with ResNet150 | ResNet150 segmentation · PASCAL VOC test | mIoU: 89.0 -> 88.5 | No clear effect |
Closest papers by meaning
- Dual Attention Network for Scene Segmentation (CVPR 2019 · similarity 0.89)
- Squeeze-and-Attention Networks for Semantic Segmentation (CVPR 2020 · similarity 0.88)
- Channelized Axial Attention – considering Channel Relation within Spatial Attention for Semantic Segmentation (AAAI 2022 · similarity 0.88)
- RANet: Region Attention Network for Semantic Segmentation (NeurIPS 2020 · similarity 0.87)
- L2G: A Simple Local-to-Global Knowledge Transfer Framework for Weakly Supervised Semantic Segmentation (CVPR 2022 · similarity 0.87)
- BFANet: Revisiting 3D Semantic Segmentation with Boundary Feature Analysis (CVPR 2025 · 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.