Research map / Architectures and efficiency / Neural architecture search
You Only Search Once: Single Shot Neural Architecture Search via Direct Sparse Optimization
Xinbang Zhang, Zehao Huang, Naiyan Wang, Shiming Xiang, Chunhong Pan
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 split training sets for weights and structure (ablation) | DSO-NAS-full · CIFAR-10 | test error (%): 3.20 -> 3.02 | Improved |
| add split training sets for weights and structure (ablation) | DSO-NAS-share · CIFAR-10 | test error (%): 3.14 -> 2.86 | Improved |
| add pre-trained weight initialization before search (ablation) | DSO-NAS-full · CIFAR-10 | test error (%): 3.26 -> 3.02 | Improved |
| add pre-trained weight initialization before search (ablation) | DSO-NAS-share · CIFAR-10 | test error (%): 3.07 -> 2.86 | Improved |
| change weight:structure update ratio from 1:1 to 4:1 (ablation) | DSO-NAS-full · CIFAR-10 | test error (%): 3.02 -> 3.05 | No clear effect |
| change weight:structure update ratio from 1:1 to 4:1 (ablation) | DSO-NAS-share · CIFAR-10 | test error (%): 2.86 -> 2.89 | No clear effect |
| use block sharing (share) instead of full search space | DSO-NAS · CIFAR-10 (with cutout) | test error (%): 2.95 -> 2.84 | No clear effect |
| use DSO-NAS searched structure instead of random structure | DSO-NAS-share · CIFAR-10 (with cutout) | test error (%): 3.58 -> 2.84 | Improved |
| search directly on ImageNet instead of transferring CIFAR-10 block | DSO-NAS · ImageNet | top-1 error (%): 26.2 -> 25.4 | Improved |
| add adaptive FLOPs regularization (ablation) | DSO-NAS · CIFAR-10 | test error | Improved |
| add adaptive MAC regularization (ablation) | DSO-NAS · CIFAR-10 | accuracy under MAC budget | Improved |
Closest papers by meaning
- ISTA-NAS: Efficient and Consistent Neural Architecture Search by Sparse Coding (NeurIPS 2020 · similarity 0.94)
- DA-NAS: Data Adapted Pruning for Efficient Neural Architecture Search (ECCV 2020 · similarity 0.92)
- AdvantageNAS: Efficient Neural Architecture Search with Credit Assignment (AAAI 2021 · similarity 0.91)
- DDPNAS: Efficient Neural Architecture Search via Dynamic Distribution Pruning (IJCV 2023 · similarity 0.91)
- Efficient Few-Shot Neural Architecture Search by Counting the Number of Nonlinear Functions (AAAI 2025 · similarity 0.90)
- EG-NAS: Neural Architecture Search with Fast Evolutionary Exploration (AAAI 2024 · 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.
