<ul><li>Deep neural networks often face performance declines due to distribution shifts between training and test domains, impacting Quality of Experience (QoE) for applications.</li><li>Existing test-time adaptation methods struggle with dynamic, multiple test distributions within batches, revealing limitations in global normalization strategies.</li><li>Feature-based Instance Neighbor Discovery (FIND) is introduced, consisting of Layer-wise Feature Disentanglement (LFD), Feature Aware Batch Normalization (FABN), and Selective FABN (S-FABN) to address these challenges.</li><li>FIND shows significant performance improvements over existing methods, achieving a 30% accuracy enhancement in dynamic scenarios while ensuring computational efficiency.</li></ul>

Feature-Based Instance Neighbor Discovery: Advanced Stable Test-Time Adaptation in Dynamic World

Discover more