Research map / Label-efficient and robust learning / Domain adaptation and generalization
Transferable Curriculum for Weakly-Supervised Domain Adaptation
Yang Shu, Zhangjie Cao, Mingsheng Long, Jianmin Wang
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 |
|---|---|---|---|
| TCL transferable curriculum instead of MentorNet | ResNet-50 domain adaptation · Office-31 40% label corruption | accuracy: 67.2 -> 76.6 | Improved |
| TCL instead of RTN | ResNet-50 · Office-31 40% mixed corruption | accuracy: 75.6 -> 81.5 | Improved |
| TCL instead of MentorNet | ResNet-50 · Office-Home 40% mixed corruption | accuracy: 53.0 -> 56.6 | Improved |
| TCL instead of RTN | ResNet-50 · Bing-Caltech | accuracy: 75.8 -> 79.0 | Improved |
| add curriculum weight on domain discriminator (ablation) | TCL · Office-31 40% mixed | accuracy: 81.0 -> 81.5 | Improved |
| add curriculum weight on label classifier (ablation) | TCL · Office-31 40% mixed | accuracy: 78.4 -> 81.5 | Improved |
| add easiness (loss) term to curriculum (ablation) | TCL · Office-31 40% mixed | accuracy: 77.3 -> 81.5 | Improved |
| add transferability term to curriculum (ablation) | TCL · Office-31 40% mixed | accuracy: 80.7 -> 81.5 | 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.
- MentorNet — MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels (ICML 2018) · 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
- Unsupervised Domain Adaptation with Residual Transfer Networks (NeurIPS 2016 · similarity 0.89)
- A General Representation-Based Approach to Multi-Source Domain Adaptation (ICML 2025 · similarity 0.89)
- De-Confusing Pseudo-Labels in Source-Free Domain Adaptation (ECCV 2024 · similarity 0.89)
- Learning to Transfer Examples for Partial Domain Adaptation (CVPR 2019 · similarity 0.89)
- Transferable Representation Learning with Deep Adaptation Networks (TPAMI 2018 · similarity 0.88)
- Transferable Adversarial Training: A General Approach to Adapting Deep Classifiers (ICML 2019 · 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.
