StableTTA: Improving Vision Model Performance by Training-free Test-Time Adaptation Methods
Ensemble methods improve predictive performance but often incur high memory and computational costs. We identify an aggregation instability induced by nonlinear projection and voting operations. To address both efficiency challenges and this inconsistency, we propose StableTTA, a training-free test-time adaptation method with two variants. StableTTA-I targets coherent-batch inference settings, where temporally or semantically adjacent observations are likely to belong to the same class. Examples include burst photography, video streams, robotics perception, and industrial inspection. Under coherent-batch inference, StableTTA-I substantially improves prediction consistency and accuracy through variance-aware logit aggregation. StableTTA-II establishes feature-level cropping, enabling efficient logit aggregation with a single forward pass on a single model backbone. Experiments on ImageNet-1K across 71 models demonstrate that StableTTA-I consistently improves prediction accuracy under coherent-batch inference, while StableTTA-II provides lightweight and architecture-agnostic accuracy improvements with minimal computational overhead. These results suggest that inference-time semantic coherence and aggregation stability provide useful perspectives for improving practical test-time adaptation systems.
Code (0)
등록된 구현이 없습니다.
Tasks
Test-time AdaptationSimilar Papers 제목 키워드 기반
Training-Free Test-Time Adaptation with Brownian Distance Covariance in Vision-Language Models
Vision-language models suffer performance degradation under domain shift, limiting real-world applicability. Existing test-time adaptation methods are computationally intensive, rely on back-propagation, and often focus …
Test-time AdaptationReward-Guided Semantic Evolution for Test-time Adaptive Object Detection
Open-vocabulary object detection with vision-language models (VLMs) such as Grounding DINO suffers from performance degradation under test-time distribution shifts, primarily due to semantic misalignment between text emb…
Object DetectionFree on the Fly: Enhancing Flexibility in Test-Time Adaptation with Online EM
Vision-Language Models (VLMs) have become prominent in open-world image recognition for their strong generalization abilities. Yet, their effectiveness in practical applications is compromised by domain shifts and distri…
Test-time AdaptationFree on the Fly: Enhancing Flexibility in Test-Time Adaptation with Online EM
Vision-Language Models (VLMs) have become prominent in open-world image recognition for their strong generalization abilities. Yet, their effectiveness in practical applications is compromised by domain shifts and di…
Test-time AdaptationVision Transformers Don't Need Trained Registers
We investigate the mechanism underlying a previously identified phenomenon in Vision Transformers -- the emergence of high-norm tokens that lead to noisy attention maps. We observe that in multiple models (e.g., CLIP, DI…