Resilient Practical Test-Time Adaptation: Soft Batch Normalization Alignment and Entropy-driven Memory Bank
This addresses practical challenges in adapting machine learning models to unseen domains during inference, though it appears incremental as it builds on existing memory bank and batch normalization techniques.
The paper tackles the problem of model performance degradation in test-time domain adaptation due to continuous distribution changes and non-i.i.d. test samples, proposing a method that achieves state-of-the-art results on benchmark datasets.
Test-time domain adaptation effectively adjusts the source domain model to accommodate unseen domain shifts in a target domain during inference. However, the model performance can be significantly impaired by continuous distribution changes in the target domain and non-independent and identically distributed (non-i.i.d.) test samples often encountered in practical scenarios. While existing memory bank methodologies use memory to store samples and mitigate non-i.i.d. effects, they do not inherently prevent potential model degradation. To address this issue, we propose a resilient practical test-time adaptation (ResiTTA) method focused on parameter resilience and data quality. Specifically, we develop a resilient batch normalization with estimation on normalization statistics and soft alignments to mitigate overfitting and model degradation. We use an entropy-driven memory bank that accounts for timeliness, the persistence of over-confident samples, and sample uncertainty for high-quality data in adaptation. Our framework periodically adapts the source domain model using a teacher-student model through a self-training loss on the memory samples, incorporating soft alignment losses on batch normalization. We empirically validate ResiTTA across various benchmark datasets, demonstrating state-of-the-art performance.