Research map / Architectures and efficiency / Neural architecture search
Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells
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 |
|---|---|---|---|
| Add intermediate supervision using auxiliary cells tied to the searched cell design (ablation) | searched segmentation architectures · PASCAL VOC (10 selected architectures) | mean IoU | Helped |
| Use auxiliary cells instead of a plain auxiliary classifier (ablation) | searched segmentation architectures · PASCAL VOC (10 selected architectures) | mean IoU: 8 out of 10 | Helped |
| Include Polyak averaging, auxiliary cells, and knowledge distillation (ablation) | sampled architectures during search · search training stages | reward | Helped |
| Combine Polyak averaging, auxiliary cells, and knowledge distillation (ablation) | sampled architectures during search · second training stage | reward | Helped |
| Use the RL controller rather than random search | architecture search · PASCAL VOC search | frequency of finding promising architectures | Helped |
Closest papers by meaning
- Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation (CVPR 2019 · similarity 0.91)
- Graph-Guided Architecture Search for Real-Time Semantic Segmentation (CVPR 2020 · similarity 0.90)
- FasterSeg: Searching for Faster Real-time Semantic Segmentation (ICLR 2020 · similarity 0.89)
- Sparse All-Layer Connector for Domain Generalised Semantic Segmentation (NeurIPS 2026 · similarity 0.88)
- OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation (CVPR 2024 · similarity 0.87)
- Learning Hierarchical Image Segmentation For Recognition and By Recognition (ICLR 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.