SOURCE-LINKED INTELLIGENCE

On the Interaction Between Model Compression and Test-Time Adaptation

arXiv · AI, language, vision and robotics · article · Sep 3, 2026 · UTC

Deep neural networks deployed in the wild must be both efficient and adaptable, requiring model compression and test-time adaptation (TTA). While both are well studied in isolation, their interaction remains poorly understood. We systematically analyze how structured compression affects a model's ability to adapt under distribution shift. Using ResNet-18 and ViT-Base on CIFAR-10-C and ImageNet-C, we evaluate multiple compression methods combined with standard TTA techniques. We introduce a diagnostic framework that examines representational expressivity and adaptation subspace compatibility. O

Read original source ↗ Open in workspace

recordType

paper

region

Global