Tianyi Ma, Maoying Qiao

Younggeol Cho, Youngrae Kim, Junho Yoon +2

Yunbei Zhang, Akshay Mehra, Jihun Hamm

Hamidreza Dastmalchi, Aijun An, Ali Cheraghian +2

Xingyu Wang, Tao Wang

Test-Time Adaptation (TTA) is essential for enabling deep learning models to handle real-world data distribution shifts. However, current approaches face significant limitations: backpropagation-based methods are not suitable for low-end deployment devices, due to their high computation and memory requirements, as well as their tendency to modify model weights during adaptation; while traditional backpropagation-free techniques exhibit constrained adaptation capabilities. In this work, we propose Forward-Only Zeroth-Order Optimization (FOZO), a novel and practical backpropagation-free paradigm

Lihua Zhou, Mao Ye, Shuaifeng Li +5