Research map / Label-efficient and robust learning / Test-time adaptation
Exposing Mixture and Annotating Confusion for Active Universal Test-Time Adaptation
Jiayao Tan, Fan Lyu, Chenggong Ni, Fuyuan Hu, Wei Feng, Rui Yao
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 EMAC active annotation on top of UTTA | OPTTT-style UTTA baselines · DomainNet avg | AH: 49.8 -> 52.2 | Improved |
| use EMAC over strongest UTTA baseline on VisDA-C | OPTTT · VisDA-C SVHN | AH: 69.2 -> 72.3 | Improved |
| use EMAC instead of generic active learning selectors (same B=1000) | TENT-wrapped AL methods · DomainNet avg | AH: 49.5 -> 52.2 | Improved |
| raise annotation budget B from 800 to 1500 (ablation) | EMAC · DomainNet avg | AH: 50.8 -> 53.1 | Improved |
| add exposing mixed candidates (EMSC) to SC+BTPO (ablation) | EMAC · DomainNet | AH: 50.8 -> 52.2 | Improved |
| add cluster-contrastive balanced loss (BTPO) to EMSC+SC (ablation) | EMAC · VisDA-C | AH: 71.7 -> 76.5 | Improved |
| add reward-guided selection (SC) to EMSC+BTPO (ablation) | EMAC · DomainNet | AH | Improved |
| add sliding window buffer and EMA for GMM at batch size 1 (ablation) | EMAC · DomainNet S2R | AH: 16.3 -> 47.3 | Improved |
| select annotation samples from GMM mixed region rather than entropy-defined region (ablation) | pseudo-label error analysis · Painting/Real/Sketch | error rate in mixed region: Xmix error 82.6/86.4/84.0 vs entropy 77.8/71.2/68.8 | Improved |
| inject 5-10% annotation noise (ablation) | EMAC (B=800) · DomainNet avg | AH-type avg: 50.8 -> 48.7 (10% error) | Hurt |
Closest papers by meaning
- Active Test-Time Adaptation: Theoretical Analyses and An Algorithm (ICLR 2024 · similarity 0.90)
- ReservoirTTA: Prolonged Test-time Adaptation for Evolving and Recurring Domains (NeurIPS 2025 · similarity 0.87)
- A Layer Selection Approach to Test Time Adaptation (AAAI 2025 · similarity 0.86)
- SCAP: Transductive Test-Time Adaptation via Supportive Clique-based Attribute Prompting (CVPR 2025 · similarity 0.86)
- AETTA: Label-Free Accuracy Estimation for Test-Time Adaptation (CVPR 2024 · similarity 0.86)
- Efficient Test-time Adaptation through Candidate Verification and Divergence Shifts (NeurIPS 2026 · 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.
