Research map / Architectures and efficiency / Neural architecture search
Powering One-shot Topological NAS with Stabilized Share-parameter Proxy
Ronghao Guo, Chen Lin, Chuming Li, Keyu Tian, Ming Sun, Lu Sheng, Junjie Yan
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 4 random skip residual blocks to ResNet-18 at equal FLOPs (topology complexity) | ResNet-18 · ImageNet val | top-1 accuracy (%): 70.2 -> 71.5 / 72.0 / 69.6 | Mixed |
| estimate architecture score by averaging SGLD-sampled shared parameters instead of a single checkpoint (ablation) | ST-NAS hyper-network · Ranking of 12 architectures | Kendall tau: 0.71 -> 0.84 | Improved |
| estimate architecture score by averaging accuracy over SGLD-sampled shared parameters (ablation) | ST-NAS hyper-network · Ranking of 12 architectures | Kendall tau: 0.71 -> 0.81 | Improved |
| add independent fine-tuning of each architecture from hyper-network weights (ablation) | ST-NAS hyper-network · Ranking of 12 architectures | Kendall tau: 0.71 -> 0.64 | Hurt |
| parameter expectation versus accuracy expectation (ablation) | SGLD sampling · Ranking of 12 architectures | Kendall tau: 0.84 vs 0.81 | No clear effect |
| use ST-NAS-A topology-augmented searched backbone instead of MobileNetV2 at equal MAdds | FPN detector · COCO | mAP: 31.7 -> 33.2 | Improved |
| use ST-NAS-B backbone instead of ResNet18 | FPN detector · COCO | mAP: 32.2 -> 35.3 | Improved |
| use channel-scaled ST-NAS-B* backbone instead of ResNet50 with a quarter of the MAdds | FPN detector · COCO | mAP: 36.9 -> 37.7 | Improved |
| search in topology augmented space instead of chain-structured space (ST-NAS-A vs SPOS) | one-shot NAS · ImageNet val | top-1 accuracy (%): 74.7 -> 76.4 | Improved |
Closest papers by meaning
- NAS-Bench-1Shot1: Benchmarking and Dissecting One-shot Neural Architecture Search (ICLR 2020 · similarity 0.90)
- HEP-NAS: Towards Efficient Few-shot Neural Architecture Search via Hierarchical Edge Partitioning (AAAI 2025 · similarity 0.90)
- Single Path One-Shot Neural Architecture Search with Uniform Sampling (ECCV 2020 · similarity 0.89)
- Few-Shot Neural Architecture Search (ICML 2021 · similarity 0.89)
- Generalizing Few-Shot NAS with Gradient Matching (ICLR 2022 · similarity 0.89)
- Efficient Few-Shot Neural Architecture Search by Counting the Number of Nonlinear Functions (AAAI 2025 · similarity 0.89)
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.
