Research map / Label-efficient and robust learning / Domain adaptation and generalization
Transferability vs. Discriminability: Batch Spectral Penalization for Adversarial Domain Adaptation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 batch spectral penalization | DANN · Office-31 avg | accuracy: 82.2 -> 87.7 | Helped |
| add batch spectral penalization | CDAN · Office-31 avg | accuracy: 86.6 -> 88.5 | Helped |
| add batch spectral penalization | DANN · Office-Home avg | accuracy: 57.6 -> 64.9 | Helped |
| add batch spectral penalization | CDAN · VisDA-2017 | mean accuracy: 73.7 -> 75.9 | Helped |
| add batch spectral penalization | ADDA · Digits avg | accuracy: 88.6 -> 93.1 | Helped |
| add batch spectral penalization | CDAN · VisDA-2017 bicycle class | accuracy: 66.9 -> 61.0 | Hurt |
| increase number of penalized singular values k from 1 to 8 (ablation) | BSP+DANN · VisDA-2017 | mean accuracy: 72.1 -> 71.5 | Hurt |
| set k=2 instead of 1 (ablation) | BSP+DANN · VisDA-2017 | mean accuracy: 72.1 -> 72.3 | No clear effect |
Closest papers by meaning
- Transferable Adversarial Training: A General Approach to Adapting Deep Classifiers (ICML 2019 · similarity 0.90)
- Cooperative and Adversarial Learning: Co-enhancing Discriminability and Transferability in Domain Adaptation (AAAI 2023 · similarity 0.90)
- Adversarially Robust Models may not Transfer Better: Sufficient Conditions for Domain Transferability from the View of Regularization (ICML 2022 · similarity 0.89)
- Bridging Theory and Algorithm for Domain Adaptation (ICML 2019 · similarity 0.87)
- Adversarial-Learned Loss for Domain Adaptation (AAAI 2020 · similarity 0.87)
- Boosting Adversarial Transferability through Augmentation in Hypothesis Space (CVPR 2025 · similarity 0.86)
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.