Decomposing the Neurons: Activation Sparsity via Mixture of Experts for Continual Test Time Adaptation

TL;DR

This paper introduces MoASE, a mixture of experts approach with activation sparsity and specialized gating mechanisms, to improve continual test-time adaptation in vision models, reducing catastrophic forgetting and enhancing performance.

Contribution

The paper proposes a novel MoASE framework with multi-gate structures and a homeostatic loss, advancing CTTA by decomposing neuron activations and adaptively combining experts.

Findings

Achieves state-of-the-art results on four benchmarks.

Effectively reduces catastrophic forgetting during adaptation.

Demonstrates superior performance in both classification and segmentation tasks.

Abstract

Continual Test-Time Adaptation (CTTA), which aims to adapt the pre-trained model to ever-evolving target domains, emerges as an important task for vision models. As current vision models appear to be heavily biased towards texture, continuously adapting the model from one domain distribution to another can result in serious catastrophic forgetting. Drawing inspiration from the human visual system's adeptness at processing both shape and texture according to the famous Trichromatic Theory, we explore the integration of a Mixture-of-Activation-Sparsity-Experts (MoASE) as an adapter for the CTTA task. Given the distinct reaction of neurons with low/high activation to domain-specific/agnostic features, MoASE decomposes the neural activation into high-activation and low-activation components with a non-differentiable Spatial Differentiate Dropout (SDD). Based on the decomposition, we devise a multi-gate structure comprising a Domain-Aware Gate (DAG) that utilizes domain information to adaptive combine experts that process the post-SDD sparse activations of different strengths, and the Activation Sparsity Gate (ASG) that adaptively assigned feature selection threshold of the SDD for different experts for more precise feature decomposition. Finally, we introduce a Homeostatic-Proximal (HP) loss to bypass the error accumulation problem when continuously adapting the model. Extensive experiments on four prominent benchmarks substantiate that our methodology achieves state-of-the-art performance in both classification and segmentation CTTA tasks. Our code is now available at https://github.com/RoyZry98/MoASE-Pytorch.