Research map / Label-efficient and robust learning / OOD and anomaly detection
Winning Prize Comes from Losing Tickets: Improve Invariant Learning by Exploring Variant Parameters for Out-of-Distribution Generalization
Zhuo Huang, Muyang Li, Li Shen, Jun Yu, Chen Gong, Bo Han, Tongliang Liu
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 EVIL sparse training | ERM · DomainBed average (ResNet-50) | accuracy: 63.8 -> 66.2 | Improved |
| add EVIL sparse training | DRO · DomainBed average (ResNet-50) | accuracy: 61.9 -> 63.8 | Improved |
| add EVIL sparse training | IRM · DomainBed average (ResNet-50) | accuracy: 63.1 -> 64.6 | Improved |
| add EVIL sparse training | SWAD · DomainBed average (ResNet-50) | accuracy: 67.2 -> 67.7 | Improved |
| add EVIL sparse training | SAM · DomainBed average (ResNet-50) | accuracy: 65.6 -> 67.5 | Improved |
| add EVIL sparse training | SAM · DomainBed TerraIncognita | accuracy: 43.3 -> 50.5 | Improved |
| use EVIL instead of SparseIRM at 60% sparsity | sparse invariant learning · DomainBed average (sparsity 60%) | accuracy: 64.8 -> 66.3 | Improved |
| use EVIL-SAM instead of SparseIRM at 80% sparsity | sparse invariant learning · DomainBed average (sparsity 80%) | accuracy: 61.7 -> 65.4 | Improved |
| use domain-label loss instead of class-label loss to explore variant parameters (EVIL vs RigL) (ablation) | EVIL · DomainBed | accuracy | Improved |
| set alpha 0.2 and Delta T 300 instead of other values (ablation) | EVIL · DomainBed | accuracy | Improved |
| initialize mask by weight value instead of connection sensitivity or random (ablation) | EVIL · DomainBed | accuracy | Improved |
| add EVIL during CLIP ViT-B/16 finetuning | CLIP ViT-B/16 · iWildCam OOD | accuracy: 35.0 -> 37.4 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- SWAD — SWAD: Domain Generalization by Seeking Flat Minima (NeurIPS 2021) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Transformation-Invariant Learning and Theoretical Guarantees for OOD Generalization (NeurIPS 2024 · similarity 0.88)
- Towards Robust Out-of-Distribution Generalization Bounds via Sharpness (ICLR 2024 · similarity 0.87)
- Sufficient Invariant Learning for Distribution Shift (CVPR 2025 · similarity 0.87)
- Out-of-distribution Generalization for Total Variation based Invariant Risk Minimization (ICLR 2025 · similarity 0.86)
- Aggregation Hides Out-of-Distribution Generalization Failures from Spurious Correlations (NeurIPS 2025 · similarity 0.86)
- OOD-Chameleon: Is Algorithm Selection for OOD Generalization Learnable? (ICML 2025 · similarity 0.85)
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.
