Research map / Label-efficient and robust learning / Domain adaptation and generalization
A Simple Feature Augmentation for Domain Generalization
Pan Li, Da Li, Wei Li, Shaogang Gong, Yanwei Fu, Timothy M. Hospedales
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 multiplicative noise to additive noise (SFA-S beta -> beta+alpha) (ablation) | SFA-S · Digit-DG | avg accuracy: 77.0 -> 79.2 | Improved |
| add adaptive noise xi to alpha and beta (ablation) | SFA-A · Digit-DG | avg accuracy: 79.2 -> 79.6 | Improved |
| use multiplicative noise only vs additive only (ablation) | SFA-S · Digit-DG | avg accuracy: 77.0 -> 78.3 | Improved |
| use Normal instead of Laplace noise (ablation) | SFA-S(beta) · Digit-DG | avg accuracy: 76.8 -> 77.0 | Improved |
| use Normal instead of uniform noise (ablation) | SFA-S(beta) · Digit-DG | avg accuracy: 76.2 -> 77.0 | Improved |
| inject noise at Layer 2 instead of Layer 0 (ablation) | SFA-S · Digit-DG | avg accuracy: 76.8 -> 79.2 | Improved |
| vary noise strength sigma from 1 to 1000 (ablation) | SFA-S · Digit-DG | avg accuracy: 79.2 vs 78.2 at sigma 1000 | No clear effect |
| add SFA feature augmentation to Vanilla ERM | Vanilla ERM · Digit-DG | avg accuracy: 73.7 -> 79.6 | Improved |
| add SFA-A to EISNet | EISNet · PACS | avg accuracy: 81.9 -> 82.5 | Improved |
| add SFA-A to DDAIG | DDAIG · PACS | avg accuracy: 81.0 -> 81.8 | Improved |
| use adaptive SFA-A instead of SFA-S | SFA · PACS | avg accuracy: 81.0 -> 81.7 | Improved |
| use adaptive SFA-A instead of SFA-S | SFA · VLCS | avg accuracy: 73.5 -> 74.0 | Improved |
Closest papers by meaning
- Multimodal Unsupervised Domain Generalization by Retrieving Across the Modality Gap (ICLR 2025 · similarity 0.90)
- Robust Domain Generalization under Divergent Marginal and Conditional Distributions (NeurIPS 2026 · similarity 0.89)
- Gradient-Guided Annealing for Domain Generalization (CVPR 2025 · similarity 0.89)
- PracticalDG: Perturbation Distillation on Vision-Language Models for Hybrid Domain Generalization (CVPR 2024 · similarity 0.89)
- AdvST: Revisiting Data Augmentations for Single Domain Generalization (AAAI 2024 · similarity 0.89)
- Rethinking Multi-domain Generalization with A General Learning Objective (CVPR 2024 · 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.
