Research map / Label-efficient and robust learning / Domain adaptation and generalization
Bringing Equity to Classification: Domain Generalization for Domain-Linked Classes
Kimathi Kaai, Saad Hossain, Sirisha Rambhatla
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 fairness objective (ablation) | FOND · High shared-class, average over 3 datasets | Y_L accuracy: 36.7 -> 43.9 | Improved |
| add fairness objective (ablation) | FOND · VLCS (High) | Y_L accuracy: 51.7 -> 72.1 | Improved |
| add fairness objective (ablation) | FOND · PACS (High) | Y_L accuracy: 17.5 -> 19.1 | Improved |
| add fairness objective (ablation) | FOND · OfficeHome (High) | Y_L accuracy: 40.8 -> 40.6 | Hurt |
| add beta term to FOND without fairness (ablation) | FOND\F · High shared-class, average | Y_L accuracy: 33.7 -> 36.7 | Improved |
| add alpha term to FOND without fairness and beta (ablation) | FOND\FB · High shared-class, average | Y_L accuracy: 35.9 -> 33.7 | Improved |
| add fairness objective (ablation) | FOND · Low shared-class, average | Y_L accuracy: 41.5 -> 41.2 | No clear effect |
| use FOND instead of ERM | ERM · High shared-class, average | Y_L accuracy: 34.3 -> 43.9 | Improved |
| use FOND instead of ERM | ERM · VLCS (High) | Y_L accuracy: 51.8 -> 72.1 | Improved |
| use FOND instead of best baseline | best baseline · Low shared-class, average | Y_L accuracy: 42.3 -> 41.2 | Hurt |
| use FOND instead of ERM across Low and High | ERM · Low/High average | Y_L accuracy: 38.3 -> 42.6 | Improved |
| use FOND instead of best baseline | best baseline · PACS (High) | Y_L accuracy: 16.2 -> 19.1 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- SelfReg — SelfReg: Self-Supervised Contrastive Regularization for Domain Generalization (ICCV 2021) · better on 3 of 3 shared results
- CORAL — CORAL: Disentangling Latent Representations in Long-Tailed Diffusion (NeurIPS 2025) · better on 2 of 2 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
- Towards Generalizing to Unseen Domains with Few Labels (CVPR 2024 · similarity 0.91)
- Failure Modes of Domain Generalization Algorithms (CVPR 2022 · similarity 0.91)
- Domain Generalization by Marginal Transfer Learning (JMLR 2021 · similarity 0.91)
- Improving Domain Generalization with Domain Relations (ICLR 2024 · similarity 0.90)
- Is Large-scale Pretraining the Secret to Good Domain Generalization? (ICLR 2025 · similarity 0.90)
- When Domain Generalization meets Generalized Category Discovery: An Adaptive Task-Arithmetic Driven Approach (CVPR 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.
