Research map / Label-efficient and robust learning / Domain adaptation and generalization
Towards Novel Target Discovery Through Open-Set Domain Adaptation
Taotao Jing, Hongfu Liu, Zhengming Ding
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 semantic attributes (full method vs visual-only variant) (ablation) | Ours · D2AwA R->A open-set DA | overall accuracy OS: 89.2 -> 94.5 | Improved |
| add semantic attributes (full method vs visual-only variant) (ablation) | Ours · I2AwA I->Aw open-set DA | overall accuracy OS: 48.7 -> 82.8 | Improved |
| add structure preserving partial alignment loss L^R (ablation) | Ours · open-set DA seen categories | accuracy | Improved |
| add binary seen/unseen classifier D (ablation) | Ours · open-set DA and semantic recovery | accuracy | Improved |
| add attribute propagation over visual graph (ablation) | Ours · semantic recovery unseen categories | unseen accuracy U | Improved |
| add visual-semantic fusion representation (ablation) | Ours · open-set DA seen and semantic recovery unseen | accuracy | Improved |
| use Ours instead of STA for unseen classes | Ours vs STA · D2AwA P->A open-set DA | unseen accuracy OS diamond: 5.7 -> 98.5 | Improved |
| use Ours instead of STA for unseen classes | Ours vs STA · D2AwA R->A open-set DA | unseen accuracy OS diamond: 7.2 -> 90.5 | Improved |
| Ours vs STA overall accuracy | Ours vs STA · D2AwA P->A open-set DA | overall accuracy OS: 82.5 -> 81.0 | Hurt |
| Ours vs zero-shot methods on unseen classes | Ours · D2AwA R->A semantic recovery | unseen accuracy U: 0.0 -> 37.8 | Improved |
| Ours without unseen attributes vs ABP* with unseen attributes | Ours · D2AwA R->A semantic recovery | unseen accuracy U: 16.2 -> 37.8 | Improved |
Closest papers by meaning
- Open-Set Graph Domain Adaptation via Separate Domain Alignment (AAAI 2024 · similarity 0.88)
- Open-Set Domain Adaptation for Semantic Segmentation (CVPR 2024 · similarity 0.88)
- ADU: Adaptive Detection of Unknown Categories in Black-Box Domain Adaptation (CVPR 2025 · similarity 0.87)
- COSDA: Counterfactual-based Susceptibility Risk Framework for Open-Set Domain Adaptation (ICML 2025 · similarity 0.87)
- Open-Set Heterogeneous Domain Adaptation: Theoretical Analysis and Algorithm (AAAI 2025 · similarity 0.86)
- Unveiling the Unknown: Unleashing the Power of Unknown to Known in Open-Set Source-Free Domain Adaptation (CVPR 2024 · 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.
