3 papers
cs.CV2025
Deformable Convolution Module with Globally Learned Relative Offsets for Fundus Vessel Segmentation
Lexuan Zhu, Yuxuan Li, Yuning Ren
Deformable convolution can adaptively change the shape of convolution kernel by learning offsets to deal with complex shape features. We propose a novel plug and play deformable co…
cs.LG2024
GradAlign for Training-free Model Performance Inference
Yuxuan Li, Yunhui Guo
Architecture plays an important role in deciding the performance of deep neural networks. However, the search for the optimal architecture is often hindered by the vast search spac…
cs.CR2024
Not Just Change the Labels, Learn the Features: Watermarking Deep Neural Networks with Multi-View Data
Yuxuan Li, Sarthak Kumar Maharana, Yunhui Guo
With the increasing prevalence of Machine Learning as a Service (MLaaS) platforms, there is a growing focus on deep neural network (DNN) watermarking techniques. These methods are…