Related Papers
COUNTS: Benchmarking Object Detectors and Multimodal Large Language Models under Distribution Shifts
Jiansheng Li, Xingxuan Zhang, Hao Zou +6
CVPR-2025broader adjacent4
distribution shift
PDFarXiv
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
CVPR-2026close adjacent8
out-of-distributiondistribution shifttest-time adaptationarxiv+1
ImageNet
PDFarXiv
Sign in to access this content