2.4k citations · 3.5k across the 43 of their papers we have counts for
5 papers · 1 filter
Understanding the Disharmony between Weight Normalization Family and Weight Decay: shifted Regularizer
Li Xiang, Chen Shuo, Xia Yan +1
The merits of fast convergence and potentially better performance of the weight normalization family have drawn increasing attention in recent years. These methods use standardizat…
Neural Image Compression and Explanation
Xiang Li, Shihao Ji
Explaining the prediction of deep neural networks (DNNs) and semantic image compression are two active research areas of deep learning with a numerous of applications in decision-c…
Spatial Group-wise Enhance: Improving Semantic Feature Learning in Convolutional Networks
Xiang Li, Xiaolin Hu, Jian Yang
The Convolutional Neural Networks (CNNs) generate the feature representation of complex objects by collecting hierarchical and different parts of semantic sub-features. These sub-f…
Selective Kernel Networks
Xiang Li, Wenhai Wang, Xiaolin Hu +1
In standard Convolutional Neural Networks (CNNs), the receptive fields of artificial neurons in each layer are designed to share the same size. It is well-known in the neuroscience…
Shape Robust Text Detection with Progressive Scale Expansion Network
Wenhai Wang, Enze Xie, Xiang Li +4
Scene text detection has witnessed rapid progress especially with the recent development of convolutional neural networks. However, there still exists two challenges which prevent…