← Search

Yurong Zhang

2 accepted papers

2024

Revealing the Dark Secrets of Extremely Large Kernel ConvNets on Robustness

ICML 2024poster

Robustness is a vital aspect to consider when deploying deep learning models into the wild. Numerous studies have been dedicated to the study of the robustness of vision transformers (ViTs), which have dominated as the mainstream backbone choice for vision tasks since the dawn of 2020s. Recently, so…

2023

Boosting Video Object Segmentation via Space-Time Correspondence Learning

CVPR 2023poster

Current top-leading solutions for video object segmentation (VOS) typically follow a matching-based regime: for each query frame, the segmentation mask is inferred according to its correspondence to previously processed and the first annotated frames. They simply exploit the supervisory signals from…