Research map / Label-efficient and robust learning / Domain adaptation and generalization
Contrastive Adaptation Network for Unsupervised Domain Adaptation
Check 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 inter-class domain discrepancy to intra-class alignment (ablation) | CAN · Office-31 | mean accuracy: 89.5 -> 90.6 | Helped |
| Add inter-class domain discrepancy to intra-class alignment (ablation) | CAN · VisDA-2017 validation | mean accuracy: 83.9 -> 87.2 | Helped |
| Use alternating clustering and feature updates rather than network-output pseudo labels (ablation) | CAN · Office-31 | mean accuracy: 88.1 -> 90.6 | Helped |
| Use alternating clustering and feature updates rather than network-output pseudo labels (ablation) | CAN · VisDA-2017 validation | mean accuracy: 77.5 -> 87.2 | Helped |
| Use class-aware sampling instead of class-agnostic sampling (ablation) | CAN · Office-31 | mean accuracy: 89.1 -> 90.6 | Helped |
| Use class-aware sampling instead of class-agnostic sampling (ablation) | CAN · VisDA-2017 validation | mean accuracy: 81.6 -> 87.2 | Helped |
| Update clustering labels and use pseudo-label cross-entropy instead of CDD (ablation) | CAN · Office-31 | mean accuracy: 83.4 -> 86.1 | Hurt |
| Fix the initial clustering pseudo labels during training (ablation) | CAN · Office-31 | mean accuracy: 79.8 -> 86.1 | Hurt |
Closest papers by meaning
- Connect, Not Collapse: Explaining Contrastive Learning for Unsupervised Domain Adaptation (ICML 2022 · similarity 0.93)
- SimProF: A Simple Probabilistic Framework for Unsupervised Domain Adaptation (AAAI 2025 · similarity 0.90)
- Can We Evaluate Domain Adaptation Models Without Target-Domain Labels? (ICLR 2024 · similarity 0.89)
- Towards Reliable Model Selection for Unsupervised Domain Adaptation: An Empirical Study and A Certified Baseline (NeurIPS 2024 · similarity 0.89)
- Low Category Uncertainty and High Training Potential Instance Learning for Unsupervised Domain Adaptation (AAAI 2024 · similarity 0.88)
- Link-based Contrastive Learning for One-Shot Unsupervised Domain Adaptation (CVPR 2025 · 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.