4 papers
Test-Time Adaptation for Tactile-Vision-Language Models
Chuyang Ye, Haoxian Jing, Qinting Jiang +4
Tactile-vision-language (TVL) models are increasingly deployed in real-world robotic and multimodal perception tasks, where test-time distribution shifts are unavoidable. Existing…
Feature-Based Instance Neighbor Discovery: Advanced Stable Test-Time Adaptation in Dynamic World
Qinting Jiang, Chuyang Ye, Dongyan Wei +4
Despite progress, deep neural networks still suffer performance declines under distribution shifts between training and test domains, leading to a substantial decrease in Quality o…
DATTA: Domain Diversity Aware Test-Time Adaptation for Dynamic Domain Shift Data Streams
Chuyang Ye, Dongyan Wei, Zhendong Liu +5
Test-Time Adaptation (TTA) addresses domain shifts between training and testing. However, existing methods assume a homogeneous target domain (e.g., single domain) at any given tim…
Discover Your Neighbors: Advanced Stable Test-Time Adaptation in Dynamic World
Qinting Jiang, Chuyang Ye, Dongyan Wei +3
Despite progress, deep neural networks still suffer performance declines under distribution shifts between training and test domains, leading to a substantial decrease in Quality o…