Reshaping the Online Data Buffering and Organizing Mechanism for Continual Test-Time Adaptation
Continual Test-Time Adaptation (CTTA) involves adapting a pre-trained source model to continually changing unsupervised target domains. In this paper, we systematically analyze the challenges of this task: online environment, unsupervised nature, and the risks of error accumulation and catastrophic forgetting under continual domain shifts. To address these challenges, we reshape the online data buffering and organizing mechanism for CTTA. We propose an uncertainty-aware buffering approach to identify and aggregate significant samples with high certainty from the unsupervised, single-pass data stream. Based on this, we propose a graph-based class relation preservation constraint to overcome catastrophic forgetting. Furthermore, a pseudo-target replay objective is used to mitigate error accumulation. Extensive experiments demonstrate the superiority of our method in both segmentation and classification CTTA tasks. Code is available at https://github.com/z1358/OBAO.
Code (1)
Tasks
Test-time AdaptationSimilar Papers 제목 키워드 기반
No Labels, No Look-Ahead: Unsupervised Online Video Stabilization with Classical Priors
We propose a new unsupervised framework for online video stabilization. Unlike methods based on deep learning that require paired stable and unstable datasets, our approach instantiates the classical stabilization pipeli…
Self-Organizing Dual-Buffer Adaptive Clustering Experience Replay (SODACER) for Safe Reinforcement Learning in Optimal Control
This paper proposes a novel reinforcement learning framework, named Self-Organizing Dual-buffer Adaptive Clustering Experience Replay (SODACER), designed to achieve safe and scalable optimal control of nonlinear systems.…
Reinforcement LearningFoundation Models for Cross-Domain EEG Analysis Application: A Survey
Electroencephalography (EEG) analysis stands at the forefront of neuroscience and artificial intelligence research, where foundation models are reshaping the traditional EEG analysis paradigm by leveraging their powerful…
Domain GeneralizationEeg DecodingPredicting nonlinear reshaping of periodic signals in optical fibre with a neural network
We deploy a supervised machine-learning model based on a neural network to predict the temporal and spectral reshaping of a simple sinusoidal modulation into a pulse train having a comb structure in the frequency domain,…
Towards MoE Deployment: Mitigating Inefficiencies in Mixture-of-Expert (MoE) Inference
Mixture-of-Experts (MoE) models have gained popularity in achieving state-of-the-art performance in a wide range of tasks in computer vision and natural language processing. They effectively expand the model capacity whi…
CPUDecoderGPULanguage Modeling+3