Research map / Detection and segmentation / CNN features
DenseASPP for Semantic Segmentation in Street Scenes
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 ASPP with densely connected atrous layers | DenseNet121 segmentation model · Cityscapes validation | mIoU: 72.0% -> 76.2% | Helped |
| use DenseNet169 instead of DenseNet121 (ablation) | DenseASPP(6, 12, 18, 24) · Cityscapes validation | mIoU: 76.2% -> 77.7% | Helped |
| use DenseNet201 instead of DenseNet121 (ablation) | DenseASPP(6, 12, 18, 24) · Cityscapes validation | mIoU: 76.2% -> 78.9% | Helped |
| use dilation rates (6, 12) (ablation) | DenseNet121 + DenseASPP · Cityscapes validation | mIoU: 76.2% -> 74.8% | Hurt |
| use dilation rates (6, 12, 18) (ablation) | DenseNet121 + DenseASPP · Cityscapes validation | mIoU: 76.2% -> 75.6% | Hurt |
| use dilation rates (3, 6, 12, 18) (ablation) | DenseNet121 + DenseASPP · Cityscapes validation | mIoU: 76.2% -> 75.7% | Hurt |
| use dilation rates (3, 6, 12, 18, 24) (ablation) | DenseNet121 + DenseASPP · Cityscapes validation | mIoU: 76.2% -> 76.6% | Helped |
| add dilation rate 30 (ablation) | DenseNet121 + DenseASPP(3, 6, 12, 18, 24) · Cityscapes validation | mIoU: 76.6% -> 76.5% | Hurt |
Closest papers by meaning
- In Defense of Pre-Trained ImageNet Architectures for Real-Time Semantic Segmentation of Road-Driving Images (CVPR 2019 · similarity 0.89)
- The Cityscapes Dataset for Semantic Urban Scene Understanding (CVPR 2016 · similarity 0.88)
- Weakly Supervised Semantic Segmentation for Driving Scenes (AAAI 2024 · similarity 0.87)
- Vanishing-Point-Guided Video Semantic Segmentation of Driving Scenes (CVPR 2024 · similarity 0.85)
- Unsupervised Semantic Segmentation Through Depth-Guided Feature Correlation and Sampling (CVPR 2024 · similarity 0.85)
- RMP-SAM: Towards Real-Time Multi-Purpose Segment Anything (ICLR 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.