Research map / Label-efficient and robust learning / Domain adaptation and generalization
Attract, Perturb, and Explore: Learning a Feature Alignment Network for Semi-supervised Domain Adaptation
Taekyung Kim, Changick Kim
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 the attraction scheme to the supervised baseline (ablation) | S+T · DomainNet (7 scenarios, 3-shot), AlexNet | accuracy (MEAN): 43.4 -> 46.1 | Improved |
| add the exploration scheme to attraction (ablation) | Attraction scheme · DomainNet (7 scenarios, 3-shot), AlexNet | accuracy (MEAN): 46.1 -> 48.3 | Improved |
| add the perturbation scheme to attraction and exploration (ablation) | Attract + Explore · DomainNet (7 scenarios, 3-shot), AlexNet | accuracy (MEAN): 48.3 -> 48.9 | Improved |
| use the proposed perturbation scheme instead of VAT (ablation) | Perturbation · DomainNet (7 scenarios, 3-shot), AlexNet | accuracy (MEAN): 42.5 -> 47.9 | Improved |
| add DANN domain-adversarial alignment (ablation) | S+T · DomainNet (7 scenarios, 3-shot), AlexNet | accuracy (MEAN): 43.4 -> 42.4 | Hurt |
| add MMD alignment (ablation) | S+T · DomainNet (7 scenarios, 3-shot), AlexNet | accuracy (MEAN): 43.4 -> 43.8 | No clear effect |
| add DANN to the supervised baseline on Office-Home | S+T · Office-Home (12 scenarios), ResNet-34 | accuracy (MEAN): 66.2 -> 63.5 | Hurt |
| add CDAN to the supervised baseline on DomainNet | S+T · DomainNet 3-shot, AlexNet | accuracy (MEAN): 43.4 -> 41.0 | Hurt |
| add ENT entropy minimization on ResNet-34 versus AlexNet | S+T · DomainNet 3-shot | accuracy (MEAN): 60.0 -> 67.6 (ResNet-34); 43.4 -> 39.8 (AlexNet) | Mixed |
| increase labeled target samples from 5 to 10 per class | ENT vs proposed · DomainNet, ResNet-34 | accuracy (MEAN): ENT 71.1 -> 74.0 vs MME 73.0; Ours 76.8 | Mixed |
Closest papers by meaning
- Forget More to Learn More: Domain-specific Feature Unlearning for Semi-supervised and Unsupervised Domain Adaptation (ECCV 2024 · similarity 0.91)
- Semi-Supervised Domain Adaptation via Minimax Entropy (ICCV 2019 · similarity 0.91)
- ECACL: A Holistic Framework for Semi-Supervised Domain Adaptation (ICCV 2021 · similarity 0.90)
- Universal Semi-Supervised Domain Adaptation by Mitigating Common-Class Bias (CVPR 2024 · similarity 0.89)
- Enhancing Domain Adaptation through Prompt Gradient Alignment (NeurIPS 2024 · similarity 0.88)
- Enhancing Semi-supervised Domain Adaptation via Effective Target Labeling (AAAI 2024 · 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.
