Research map / Detection and segmentation / CNN features
Gated Fully Fusion 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 |
|---|---|---|---|
| Replace ungated feature fusion with GFF (ablation) | PSPNet · Cityscapes validation | mIoU: 78.6 -> 80.4 | Helped |
| Use concatenation for feature fusion instead of the PSPNet baseline (ablation) | PSPNet · Cityscapes validation | mIoU: 78.6 -> 78.8 (0.2↑) | Helped |
| Use addition for feature fusion instead of the PSPNet baseline (ablation) | PSPNet · Cityscapes validation | mIoU: 78.6 -> 78.7 (0.1↑) | Helped |
| Add gates to the FPN top-down pathway (ablation) | PSPNet + FPN · Cityscapes validation | mIoU: 79.3 -> 79.4 (0.8 ↑) | Helped |
| Add DFP after GFF (ablation) | PSPNet + GFF · Cityscapes validation | mIoU: 80.4 -> 81.2 (2.6↑) | Helped |
| Use multi-scale inference (ablation) | PSPNet + GFF + DFP · Cityscapes validation | mIoU: 81.2 -> 81.8 (3.2↑) | Helped |
| Add GFF to DenseASPP (ablation) | DenseASPP · Cityscapes validation | mIoU: 78.9 -> 80.1(1.2↑) | Helped |
| Add DFP to DenseASPP + GFF (ablation) | DenseASPP + GFF · Cityscapes validation | mIoU: 80.1(1.2↑) -> 80.9(2.0↑) | Helped |
| Add GFF to PSP (ablation) | PSP with ResNet18 · Cityscapes validation | mIoU: 73.0 -> 76.6 (3.6↑) | Helped |
| Add DFP to PSP + GFF (ablation) | PSP with ResNet18 · Cityscapes validation | mIoU: 76.6 (3.6↑) -> 78.9 (5.9↑) | Helped |
| Apply GFF (ablation) | DenseASPP · Cityscapes validation | mIoU: 78.9 -> 80.1(1.2↑) | Helped |
Closest papers by meaning
- Hierarchically Gated Deep Networks for Semantic Segmentation (CVPR 2016 · similarity 0.89)
- Learning Fully Dense Neural Networks for Image Semantic Segmentation (AAAI 2019 · similarity 0.86)
- Dense Decoder Shortcut Connections for Single-Pass Semantic Segmentation (CVPR 2018 · similarity 0.86)
- SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation (CVPR 2024 · similarity 0.85)
- Sparse All-Layer Connector for Domain Generalised Semantic Segmentation (NeurIPS 2026 · similarity 0.85)
- Enhancing Generalized Few-Shot Semantic Segmentation via Effective Knowledge Transfer (AAAI 2025 · similarity 0.85)
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.