arXiv Machine Learning
Rethinking the Teacher-Student Framework for Test-Time Adaptation
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Jul 28
Source-Free Controlled Adaptation of Teachers for Continual Test-Time Adaptation
arXiv:2607. 23735v1 Announce Type: new Abstract: In many real-world scenarios, encountering continual shifts in domain during inference is very common.
arXiv Computer Vision
1d ago
DESA-TTA: Dynamic EMA and Source Anchoring for Test-Time Adaptation
arXiv:2609.01795v1 Announce Type: new Abstract: Vision-language object detectors (VLODs) achieve strong zero-shot performance but remain vulnerable to distribution shifts during deployment. Mean-teac...
arXiv Machine Learning
Jul 20
SloMo-Fast: Slow-Momentum and Fast-Adaptive Teachers for Source-Free Continual Test-Time Adaptation
arXiv:2511. 18468v2 Announce Type: replace Abstract: Continual Test-Time Adaptation (CTTA) is crucial for deploying models in real-world applications with unseen, evolving target domains.
Hugging Face Trending Papers
Jul 9
Continual Test-Time Adaptation in Computer Vision: Methods, Benchmarks, and Future Directions
Deep neural nets achieve remarkable performance when training and test data share the same distribution, but this assumption frequently breaks in real-world deployment, where data undergoes continual distributional shifts. Continual Test-Time Adaptation (CTTA) addresses this challenge by adapting pretrained models to non-stationary target distributions on-the-fly, without access to source data or labeled targets, while mitigating two critical failure modes: catastrophic forgetting of source knowledge and error accumulation from noisy pseudo-labels over extended time horizons.
arXiv AI
Jul 1
BP-TTA: Balanced and Prototype-Guided Test-Time Adaptation in Dynamic Scenarios
arXiv:2606. 31420v1 Announce Type: new Abstract: Test-Time Adaptation (TTA) enables models trained on a source domain to adapt online to unlabeled test data under distribution shifts.
arXiv Machine Learning
Aug 4
Learning What to Remember: Test-Time Training via Context Distillation
arXiv:2608. 01672v1 Announce Type: cross Abstract: Effective long-context modeling is not merely about retaining more of the past, but about preserving the information that may prove relevant later.