Research map / Label-efficient and robust learning / Domain adaptation and generalization
Energy-based Self-Training and Normalization for Unsupervised Domain Adaptation
Samitha Herath, Basura Fernando, Ehsan Abbasnejad, Munawar Hayat, Shahram Khadivi, Mehrtash Harandi, Hamid Rezatofighi, Gholamreza Haffari
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 free-energy based instance selection to PACMAC consistency selection (joint selection) (ablation) | self-training for UDA · DomainNet (average) | top-1 accuracy: 80.9 -> 81.5 | Improved |
| add free-energy based instance selection to PACMAC consistency selection (joint selection) (ablation) | self-training for UDA · OfficeHome (average) | top-1 accuracy: 66.8 -> 67.1 | Improved |
| use free-energy selection alone (marginal) instead of consistency alone (ablation) | self-training for UDA · DomainNet (average) | top-1 accuracy: 80.9 -> 80.7 | No clear effect |
| select low free-energy instances (proposed) rather than inverted rule, in joint selection (ablation) | joint instance selection · DomainNet (average) | top-1 accuracy: 80.1 -> 81.5 | Improved |
| invert free-energy selection rule in marginal-only case (Sel-high vs Sel-low) (ablation) | marginal instance selection · DomainNet (average) | top-1 accuracy: 80.7 -> 81.1 | Mixed |
| add SCON normalization to free-energy alignment (SCAL) (ablation) | SCAL · DomainNet (average) | top-1 accuracy: 77.2 -> 82.1 | Improved |
| add SCON normalization to free-energy alignment (SCAL) (ablation) | SCAL · OfficeHome (average) | top-1 accuracy: 63.2 -> 68.2 | Improved |
| use SCON normalization alone without SCAL alignment (ablation) | SEEBS+ · DomainNet (average) | top-1 accuracy: 70.1 -> 46.4 | Hurt |
| use proposed SCON loss instead of naive BatchNorm (ablation) | SEEBS+ · DomainNet (average) | top-1 accuracy: 81.4 -> 83.3 | Improved |
| use proposed SCON loss instead of naive BatchNorm (ablation) | SEEBS+ · OfficeHome (average) | top-1 accuracy: 68.0 -> 68.5 | Improved |
| add SCAL and SCON modules to SEEBS (ablation) | SEEBS · DomainNet (average) | top-1 accuracy: 81.5 -> 83.3 | Improved |
| energy-based selection (SEEBS) instead of PACMAC | ViT UDA self-training · VISDA2017 | accuracy: 77.1 -> 79.1 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- SENTRY — SENTRY: Selective Entropy Optimization via Committee Consistency for Unsupervised Domain Adaptation (ICCV 2021) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Active Learning for Domain Adaptation: An Energy-Based Approach (AAAI 2022 · similarity 0.90)
- Enhancing Domain Adaptation through Prompt Gradient Alignment (NeurIPS 2024 · similarity 0.88)
- Tackling Dimensional Collapse toward Comprehensive Universal Domain Adaptation (ICML 2025 · similarity 0.88)
- Towards Reliable Model Selection for Unsupervised Domain Adaptation: An Empirical Study and A Certified Baseline (NeurIPS 2024 · similarity 0.87)
- Can We Evaluate Domain Adaptation Models Without Target-Domain Labels? (ICLR 2024 · similarity 0.87)
- Prompt-Based Distribution Alignment for Unsupervised Domain Adaptation (AAAI 2024 · similarity 0.87)
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.
