Research map / Architectures and efficiency / Neural architecture search
NAS-OoD: Neural Architecture Search for Out-of-Distribution Generalization
Haoyue Bai, Fengwei Zhou, Lanqing Hong, Nanyang Ye, S.-H. Gary Chan, Zhenguo Li
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 |
|---|---|---|---|
| use searched NAS-OoD architecture instead of DecAug ResNet-18 | ResNet-18 OoD baselines · NICO (average) | accuracy: 82.67 -> 85.16 | Improved |
| use NAS-OoD instead of best OoD baseline | L2A-OT / DecAug · PACS (ImageNet-pretrained) | accuracy: 82.80 -> 84.23 | Improved |
| use NAS-OoD instead of best baseline | MMD · OoD-FP | accuracy: 95.83 -> 98.77 | Improved |
| use NAS-OoD instead of best baseline when trained from scratch | DecAug · PACS (from scratch) | accuracy: 50.96 -> 53.80 | Improved |
| search architecture with conditional generator (add NAS-OoD) instead of plain NAS (ablation) | DARTS · NICO (average) | accuracy: 79.61 -> 85.16 | Improved |
| add IRM regularizer to NAS methods (ablation) | DARTS · NICO (average) | accuracy: 79.61 -> 77.26 | Hurt |
| add IRM regularizer to NAS methods (ablation) | SNAS · NICO (average) | accuracy: 83.00 -> 79.73 | Hurt |
| add IRM regularizer to NAS methods (ablation) | ISTA-NAS · NICO (average) | accuracy: 83.63 -> 80.09 | Hurt |
| add REx regularizer to NAS methods (ablation) | SNAS · NICO (average) | accuracy: 83.00 -> 71.23 | Hurt |
| add NAS-OoD search instead of random architecture sampling (ablation) | random architecture · NICO (average) | accuracy: 78.68 -> 85.16 | Improved |
| add generator cycle-consistency loss (ablation) | NAS-OoD · NICO (average) | accuracy: 83.86 -> 85.16 | Improved |
| add NAS-OoD architecture search instead of NAS+IRM (ablation) | NAS + IRM · PACS (ImageNet-pretrained) | accuracy: 78.93 -> 83.89 | Improved |
Closest papers by meaning
- Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights (NeurIPS 2024 · similarity 0.91)
- OoD-Bench: Quantifying and Understanding Two Dimensions of Out-of-Distribution Generalization (CVPR 2022 · similarity 0.89)
- Generalization Guarantees for Neural Architecture Search with Train-Validation Split (ICML 2021 · similarity 0.89)
- Robust NAS under adversarial training: benchmark, theory, and beyond (ICLR 2024 · similarity 0.88)
- Robustifying and Boosting Training-Free Neural Architecture Search (ICLR 2024 · similarity 0.88)
- Insights from the Use of Previously Unseen Neural Architecture Search Datasets (CVPR 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.
