Research map / Label-efficient and robust learning / Domain adaptation and generalization
Adversarial Partial Domain Adaptation by Cycle Inconsistency
Kun-Yu Lin, Jiaming Zhou, Yukun Qiu, Wei-Shi Zheng
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 cycle-inconsistency sample weighting to DANN (ablation) | DANN · Office-Home PDA | avg accuracy: 55.88 -> 76.72 | Improved |
| add center losses (ablation) | Ours-Cycle · Office-Home PDA | avg accuracy: 76.72 -> 77.72 | Improved |
| use soft nearest neighbor instead of hard prototype search (ablation) | Ours-Cycle · Office-Home PDA | avg accuracy: 77.44 -> 77.72 | Improved |
| add cycle-back transformation (ablation) | Ours-Src2Trg · Office-Home PDA | avg accuracy: 76.33 -> 77.72 | Improved |
| add mixed strategy with source-to-target term (ablation) | Ours-Cycle · Office-Home PDA | avg accuracy: 77.72 -> 78.83 | Improved |
| initialize with source-only model | IWAN · Office-Home PDA | avg accuracy: 69.87 -> 73.04 | Improved |
| initialize with source-only model | ETN · Office-Home PDA | avg accuracy: 70.45 -> 67.65 | Mixed |
| initialize with source-only model | ETN · VisDA-2017 PDA | avg accuracy: 66.84 -> 64.15 | Hurt |
| apply DANN adversarial alignment with no weighting | source-only model · Office-Home PDA | avg accuracy: 61.77 -> 55.88 | Hurt |
| use cycle weighting vs prior weighted adversarial methods | Ours · VisDA-2017 PDA | Re.->Sy. accuracy: 78.18 -> 86.50 | Improved |
Closest papers by meaning
- Partial Adversarial Domain Adaptation (ECCV 2018 · similarity 0.91)
- A Balanced and Uncertainty-aware Approach for Partial Domain Adaptation (ECCV 2020 · similarity 0.91)
- Discriminative Partial Domain Adversarial Network (ECCV 2020 · similarity 0.90)
- Importance Weighted Adversarial Nets for Partial Domain Adaptation (CVPR 2018 · similarity 0.90)
- Maximum Classifier Discrepancy for Unsupervised Domain Adaptation (CVPR 2018 · similarity 0.89)
- Towards Accurate and Robust Domain Adaptation Under Multiple Noisy Environments (TPAMI 2022 · 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.
