Research map / Label-efficient and robust learning / Test-time adaptation
SaTeen: Learning Structural Alignment for Continual Test-Time Adaptation
Chang Liu, Ruotong Zhao, Li Gao, Yupei Zhang
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 inter-sample structure alignment to intra-sample alignment (ablation) | SaTeen (ResNet50-GN) · ImageNet-C single TTA | accuracy: 47.1 -> 49.9 | Improved |
| add inter-sample structure alignment to intra-sample alignment (ablation) | SaTeen (VitBase-LN) · ImageNet-C single TTA | accuracy: 65.1 -> 65.4 | Improved |
| add inter-sample structure alignment to intra-sample alignment (ablation) | SaTeen (ResNet50-GN) · ImageNet-C continual TTA | accuracy: 43.2 -> 47.1 | Improved |
| add inter-sample structure alignment to intra-sample alignment (ablation) | SaTeen (VitBase-LN) · ImageNet-C continual TTA | accuracy: 62.7 -> 64.6 | Improved |
| use SaTeen instead of DeYO | ResNet18-BN · ColoredMNIST | worst-group accuracy: 52.7 -> 67.2 | Improved |
| use SaTeen instead of DeYO | ResNet50-BN · Waterbirds | worst-group accuracy: 74.6 -> 76.3 | Improved |
| use SaTeen instead of DeYO | ResNet50-GN · ImageNet-C continual TTA | accuracy: 40.1 -> 47.1 | Improved |
| use SaTeen instead of DeYO | VitBase-LN · ImageNet-C continual TTA | accuracy: 61.6 -> 64.6 | Improved |
| use SaTeen instead of DeYO | ResNet50-GN · ImageNet-C single TTA | accuracy: 42.4 -> 49.9 | Improved |
| use intra-sample alignment alone without sample selection (ablation) | SaTeen · ImageNet-C continual TTA | accuracy | Improved |
| define negative sample by randomly drawing another batch instance (ablation) | SaTeen · ImageNet-C mild scenarios | accuracy | Mixed |
| use SaTeen instead of Tent | VitBase-LN · ImageNet-C continual TTA time | accuracy: 49.0 -> 64.6 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- Tent — Tent: Fully Test-Time Adaptation by Entropy Minimization (ICLR 2021) · better on 4 of 4 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
- Test-time Correlation Alignment (ICML 2025 · similarity 0.89)
- Unified Entropy Optimization for Open-Set Test-Time Adaptation (CVPR 2024 · similarity 0.89)
- Backpropagation-Free Test-Time Adaptation via Probabilistic Gaussian Alignment (NeurIPS 2025 · similarity 0.88)
- Test-Time Adaptation on Noisy Data via Model-Pruning-Based Filtering and Flatness-Aware Entropy Minimization (AAAI 2025 · similarity 0.88)
- Everything to the Synthetic: Diffusion-driven Test-time Adaptation via Synthetic-Domain Alignment (CVPR 2025 · similarity 0.88)
- A Layer Selection Approach to Test Time Adaptation (AAAI 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.
