4 papers
Self-supervised Dynamic Heterogeneous Degradation Modeling for Unified Zero-Shot Image Restoration
XiaoWan Hu, Jing Yang, HeNan Liu +2
Zero-shot image restoration provides a flexible way to handle diverse degradations without task-specific training. However, existing methods typically rely on stacked layers or pre…
U2-BENCH: Benchmarking Large Vision-Language Models on Ultrasound Understanding
Anjie Le, Henan Liu, Yue Wang +18
Ultrasound is a widely-used imaging modality critical to global healthcare, yet its interpretation remains challenging due to its varying image quality on operators, noises, and an…
Continuous Patch Stitching for Block-wise Image Compression
Zifu Zhang, Shengxi Li, Henan Liu +2
Most recently, learned image compression methods have outpaced traditional hand-crafted standard codecs. However, their inference typically requires to input the whole image at the…
ANAct: Adaptive Normalization for Activation Functions
Yuan Peiwen, Henan Liu, Zhu Changsheng +1
In this paper, we investigate the negative effect of activation functions on forward and backward propagation and how to counteract this effect. First, We examine how activation fu…