BECoTTA: Input-dependent Online Blending of Experts for Continual Test-time Adaptation
Continual Test Time Adaptation (CTTA) is required to adapt efficiently to continuous unseen domains while retaining previously learned knowledge. However, despite the progress of CTTA, it is still challenging to deploy the model with improved forgetting-adaptation trade-offs and efficiency. In addition, current CTTA scenarios assume only the disjoint situation, even though real-world domains are seamlessly changed. To address these challenges, this paper proposes BECoTTA, an input-dependent and efficient modular framework for CTTA. We propose Mixture-of Domain Low-rank Experts (MoDE) that contains two core components: (i) Domain-Adaptive Routing, which helps to selectively capture the domain adaptive knowledge with multiple domain routers, and (ii) Domain-Expert Synergy Loss to maximize the dependency between each domain and expert. We validate that our method outperforms multiple CTTA scenarios, including disjoint and gradual domain shits, while only requiring ~98% fewer trainable parameters. We also provide analyses of our method, including the construction of experts, the effect of domain-adaptive experts, and visualizations.
Code (0)
등록된 구현이 없습니다.
Tasks
Test-time AdaptationSimilar Papers 제목 키워드 기반
CoCoAFusE: Beyond Mixtures of Experts via Model Fusion
Many learning problems involve multiple patterns and varying degrees of uncertainty dependent on the covariates. Advances in Deep Learning (DL) have addressed these issues by learning highly nonlinear input-output depend…
Mixture-of-ExpertsPhilosophyUncertainty QuantificationWhen AI Gives Advice: Evaluating AI and Human Responses to Online Advice-Seeking for Well-Being
Seeking advice is a core human behavior that the internet has reinvented twice: first through forums and Q&A communities that crowdsource public guidance, and now through large language models (LLMs). Yet the quality of …
Replicable Online Learning
We investigate the concept of algorithmic replicability introduced by Impagliazzo et al. 2022, Ghazi et al. 2021, Ahn et al. 2024 in an online setting. In our model, the input sequence received by the online learner is g…
Deep Blending for Free-Viewpoint Image-Based-Rendering
Free-viewpoint image-based rendering (IBR) is a standing challenge. IBR methods combine warped versions of input photos to synthesize a novel view. The image quality of this combination is directly affected by geometric …
Novel View SynthesisExplainable data-driven modeling via mixture of experts: towards effective blending of grey and black-box models
Traditional models grounded in first principles often struggle with accuracy as the system's complexity increases. Conversely, machine learning approaches, while powerful, face challenges in interpretability and in handl…
Mixture-of-Experts