Research map / Label-efficient and robust learning / Domain adaptation and generalization
Visualizing Adapted Knowledge in Domain Transfer
Yunzhong Hou, Liang Zheng
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 |
|---|---|---|---|
| Generate source-style images from target images using the two models as guidance | SFIT · Digits, Office-31, and VisDA | recognition accuracy on generated images: 26.5% to 0.2%; 7.6% to 0.7%; 25.2% to 0.3%; 8.0% to 1.7%; 33.9% to 6.9% | Improved |
| Fine-tune the target model using generated-image cues and target images | Target model · Office-31 | accuracy: 0.4% | Improved |
| Fine-tune the target model using generated-image cues and target images | Target model · VisDA | accuracy: 0.7% | Improved |
| Add the knowledge distillation loss (ablation) | SFIT · VisDA | accuracy: 1.1% | Improved |
| Add the channel-wise relationship preserving loss (ablation) | SFIT · VisDA | accuracy: 2.6% | Improved |
| Replace channel-wise relationship preserving loss with traditional style loss (ablation) | SFIT · VisDA | accuracy: 4.8% | Hurt |
| Replace channel-wise relationship preserving loss with batch-wise relationship loss (ablation) | SFIT · VisDA | accuracy: 71.2; 71.2 | No clear effect |
| Replace channel-wise relationship preserving loss with pixel-wise relationship loss (ablation) | SFIT · VisDA | accuracy: 70.9; 71.2 | No clear effect |
| Use transparent-filter initialization rather than the original target images (ablation) | SFIT generator · VisDA | accuracy: 46.8 -> 44.9 | Hurt |
Closest papers by meaning
- End-to-End Knowledge Distillation for Unsupervised Domain Adaptation with Large Vision-language Models (AAAI 2026 · similarity 0.88)
- Where and How to Transfer: Knowledge Aggregation-Induced Transferability Perception for Unsupervised Domain Adaptation (TPAMI 2021 · similarity 0.88)
- Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation (ICML 2020 · similarity 0.88)
- Adapting to Distribution Shift by Visual Domain Prompt Generation (ICLR 2024 · similarity 0.87)
- Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer (TPAMI 2021 · similarity 0.87)
- A General Representation-Based Approach to Multi-Source Domain Adaptation (ICML 2025 · similarity 0.85)
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.
