Reliability-Gated Source Anchoring for Continual Test-Time Adaptation
Continual test-time adaptation (CTTA) updates a pretrained model online on an unlabeled, non-stationary stream while anchoring it to a frozen source checkpoint. This anchor is useful only when the source remains reliable. On CCC-Hard, however, a ResNet-50 source falls to approximately $1.3\%$ top-$1$ accuracy, while existing source-anchored CTTA methods continue applying the same anchor strength. We call this failure mode blind anchoring and propose RMemSafe, a reliability-gated extension of ROID that uses the frozen source's normalized predictive entropy to attenuate all explicit source-coupled uses in the objective. When the source posterior approaches uniformity, the gate closes: the source anchor and agreement filter vanish, and the objective reduces to a source-agnostic fallback comprising ROID's base losses plus marginal calibration. Combined with ASR, RMemSafe achieves the lowest error on $8$ of $9$ matched-split continual-corruption cells and is the best reset-based method on all $9$, improving ROID+ASR by $1.05$~pp on ResNet-50 and $0.48$~pp on ViT-B/16. A controlled source-degradation sweep shows a $1.13{\times}$ shallower harm slope than ROID+ASR, consistent with the graceful-decay prediction. The entropy gate detects high-entropy source collapse, not confidently wrong low-entropy sources; this scope is explicitly evaluated and discussed.
Code (0)
등록된 구현이 없습니다.
Tasks
Test-time AdaptationSimilar Papers 제목 키워드 기반
SATA: Source Anchoring and Target Alignment Network for Continual Test Time Adaptation
Adapting a trained model to perform satisfactorily on continually changing testing domains/environments is an important and challenging task. In this work, we propose a novel framework, SATA, which aims to satisfy the fo…
Test-time AdaptationHow Does Cognitive Bias Affect Large Language Models? A Case Study on the Anchoring Effect in Price Negotiation Simulations
Cognitive biases, well-studied in humans, can also be observed in LLMs, affecting their reliability in real-world applications. This paper investigates the anchoring effect in LLM-driven price negotiations. To this end, …
Mitigating the Bias in the Model for Continual Test-Time Adaptation
Continual Test-Time Adaptation (CTA) is a challenging task that aims to adapt a source pre-trained model to continually changing target domains. In the CTA setting, a model does not know when the target domain changes, t…
Test-time AdaptationContinual GUI Agents
As digital environments (data distribution) are in flux, with new GUI data arriving over time-introducing new domains or resolutions-agents trained on static environments deteriorate in performance. In this work, we intr…
Continual LearningRobust Deep Reinforcement Learning Scheduling via Weight Anchoring
Questions remain on the robustness of data-driven learning methods when crossing the gap from simulation to reality. We utilize weight anchoring, a method known from continual learning, to cultivate and fixate desired be…
Continual LearningDeep Reinforcement Learningreinforcement-learningReinforcement Learning+1