Research map / Label-efficient and robust learning / Domain adaptation and generalization
Cross Contrasting Feature Perturbation for Domain Generalization
Chenming Li, Daoan Zhang, Wenjian Huang, Jianguo Zhang
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 CCFP (learnable domain perturbation with semantic consistency) to ERM | ResNet-50 ERM · PACS | average accuracy: 83.6 -> 86.6 | Improved |
| add explicit semantic consistency loss L_sem (ablation) | CCFP · PACS | average accuracy: 86.0 -> 86.6 | Improved |
| CCFP without L_sem versus ERM (ablation) | CCFP · PACS | average accuracy: 83.6 -> 86.0 | Improved |
| add dual-stream semantic consistency to Mixstyle (ablation) | Mixstyle · PACS | average accuracy: 84.9 -> 85.2 | Improved |
| add dual-stream semantic consistency to DSU (ablation) | DSU · PACS | average accuracy: 84.1 -> 85.5 | Improved |
| insert LDP modules at all five positions instead of three (ablation) | CCFP · PACS | average accuracy: 85.4 -> 86.6 | Improved |
| apply CCFP on top of SWAD | SWAD · TerraIncognita | average accuracy: 50.0 -> 53.0 | Improved |
| apply CCFP on top of SWAD | SWAD · VLCS | average accuracy: 79.1 -> 79.4 | Improved |
| CCFP versus Mixstyle on the Sketch domain of PACS | CCFP · PACS (Sketch) | accuracy: 81.6 (Mixstyle) vs 81.4 (CCFP) | No clear effect |
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 3 of 3 shared results
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
- Unknown Domain Inconsistency Minimization for Domain Generalization (ICLR 2024 · similarity 0.89)
- Is Large-scale Pretraining the Secret to Good Domain Generalization? (ICLR 2025 · similarity 0.89)
- Robust Domain Generalization under Divergent Marginal and Conditional Distributions (NeurIPS 2026 · similarity 0.89)
- PracticalDG: Perturbation Distillation on Vision-Language Models for Hybrid Domain Generalization (CVPR 2024 · similarity 0.89)
- One-Step Generalization Ratio Guided Optimization for Domain Generalization (ICML 2025 · similarity 0.88)
- Towards Generalizing to Unseen Domains with Few Labels (CVPR 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.
