Discover Your Neighbors: Advanced Stable Test-Time Adaptation in Dynamic World

TL;DR

This paper introduces DYN, a novel test-time adaptation method that leverages instance normalization clustering and cluster-aware batch normalization to improve neural network robustness under dynamic distribution shifts.

Contribution

DYN is the first backward-free approach for dynamic TTA, combining instance normalization clustering with cluster-aware batch normalization for robust adaptation.

Findings

DYN maintains high performance under dynamic data streams

It effectively clusters similar samples for better adaptation

Experimental results show improved robustness and accuracy

Abstract

Despite progress, deep neural networks still suffer performance declines under distribution shifts between training and test domains, leading to a substantial decrease in Quality of Experience (QoE) for multimedia applications. Existing test-time adaptation (TTA) methods are challenged by dynamic, multiple test distributions within batches. This work provides a new perspective on analyzing batch normalization techniques through class-related and class-irrelevant features, our observations reveal combining source and test batch normalization statistics robustly characterizes target distributions. However, test statistics must have high similarity. We thus propose Discover Your Neighbours (DYN), the first backward-free approach specialized for dynamic TTA. The core innovation is identifying similar samples via instance normalization statistics and clustering into groups which provides consistent class-irrelevant representations. Specifically, Our DYN consists of layer-wise instance statistics clustering (LISC) and cluster-aware batch normalization (CABN). In LISC, we perform layer-wise clustering of approximate feature samples at each BN layer by calculating the cosine similarity of instance normalization statistics across the batch. CABN then aggregates SBN and TCN statistics to collaboratively characterize the target distribution, enabling more robust representations. Experimental results validate DYN's robustness and effectiveness, demonstrating maintained performance under dynamic data stream patterns.