Research map / Architectures and efficiency / Neural architecture search
DCNAS: Densely Connected Neural Architecture Search for Semantic Image Segmentation
Check 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 |
|---|---|---|---|
| Use proxyless search instead of proxy-based search (ablation) | DCNAS with dense connections · Cityscapes validation | T-mIoU: 78.9 -> 81.2 | Helped |
| Use proxyless search instead of proxy-based search (ablation) | DCNAS with dense connections · Cityscapes validation | S-mIoU: 61.5 -> 69.9 | Helped |
| Add dense connections rather than limiting connections to previous layers (ablation) | DCNAS with proxyless search · Cityscapes validation | T-mIoU: 73.3 -> 81.2 | Helped |
| Add dense connections rather than limiting connections to previous layers (ablation) | DCNAS with proxyless search · Cityscapes validation | S-mIoU: 51.7 -> 69.9 | Helped |
Closest papers by meaning
- Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation (CVPR 2019 · similarity 0.90)
- Densely Connected Search Space for More Flexible Neural Architecture Search (CVPR 2020 · similarity 0.89)
- FasterSeg: Searching for Faster Real-time Semantic Segmentation (ICLR 2020 · similarity 0.89)
- Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells (CVPR 2019 · similarity 0.88)
- Searching for Efficient Multi-Scale Architectures for Dense Image Prediction (NeurIPS 2018 · similarity 0.88)
- Customizable Architecture Search for Semantic Segmentation (CVPR 2019 · similarity 0.88)
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.