Research map / Label-efficient and robust learning / Domain adaptation and generalization
Attention Diversification for Domain Generalization
Rang Meng, Xianfeng Li, Weijie Chen, Shicai Yang, Jie Song, Xinchao Wang, Lei Zhang, Mingli Song, Di Xie, Shiliang Pu
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 Inter-ADR (L_dir + L_dvr) on top of Intra-ADR (ablation) | Intra-ADR · PACS (ResNet-18) | avg accuracy (%): 84.9 -> 85.6 | Improved |
| add L_dir to Intra-ADR (ablation) | Intra-ADR · PACS (ResNet-18) | avg accuracy (%): 84.9 -> 85.4 | Improved |
| add L_dvr to Intra-ADR (ablation) | Intra-ADR · PACS (ResNet-18) | avg accuracy (%): 84.9 -> 85.2 | Improved |
| add L_dvr to Intra-ADR + L_dir (ablation) | Intra-ADR + L_dir · PACS (ResNet-18) | avg accuracy (%): 85.4 -> 85.6 | Improved |
| add Intra-ADR loss to Inter-ADR (ablation) | Inter-ADR only · PACS (ResNet-18) | avg accuracy (%): 85.0 -> 85.6 | Improved |
| add spatial expanding E_s to Intra-ADR (ablation) | Intra-ADR · PACS (ResNet-18) | avg accuracy (%): 83.0 -> 84.0 | Improved |
| add channel expanding E_c to Intra-ADR (ablation) | Intra-ADR · PACS (ResNet-18) | avg accuracy (%): 83.0 -> 83.5 | Improved |
| add both E_s and E_c (ablation) | Intra-ADR · PACS (ResNet-18) | avg accuracy (%): 83.0 -> 84.9 | Improved |
| apply Intra-ADR at res4 instead of res1 (ablation) | Intra-ADR · PACS (ResNet-18) | avg accuracy (%): 83.5 -> 84.9 | Improved |
| apply Inter-ADR on res1-4 instead of res1 only (ablation) | Inter-ADR · PACS (ResNet-18) | avg accuracy (%): 85.2 -> 85.6 | Improved |
| increase selected channels k from 2 to 10 at s=2 (ablation) | Intra-ADR · PACS (ResNet-18) | avg accuracy (%): 84.1 -> 84.9 | Improved |
| add MixStyle to I2-ADR | I2-ADR · PACS (ResNet-50) | avg accuracy (%): 88.2 -> 89.2 | 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.
- SelfReg — SelfReg: Self-Supervised Contrastive Regularization for Domain Generalization (ICCV 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
- Deep Adversarial Attention Alignment for Unsupervised Domain Adaptation: the Benefit of Target Expectation Maximization (ECCV 2018 · similarity 0.87)
- Attention Bridging Network for Knowledge Transfer (ICCV 2019 · similarity 0.86)
- Domain Generalization in CLIP via Learning with Diverse Text Prompts (CVPR 2025 · similarity 0.86)
- START: A Generalized State Space Model with Saliency-Driven Token-Aware Transformation (NeurIPS 2024 · similarity 0.85)
- CLIPCEIL: Domain Generalization through CLIP via Channel rEfinement and Image-text aLignment (NeurIPS 2024 · similarity 0.85)
- STILL: Selecting Tokens for Intra-Layer Hybrid Attention to Linearize LLMs (NeurIPS 2026 · 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.
