Xiangyu Zhang
Chongqing University of Posts and Telecommunications · 320 works · 313,751 citations · h-index 71
Top works
- Deep Residual Learning for Image Recognition
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
- Identity Mappings in Deep Residual Networks
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
- ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
- Object Detection Networks on Convolutional Feature Maps
- Deep Residual Learning for Image Recognition
- ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
- Channel Pruning for Accelerating Very Deep Neural Networks
- Large Kernel Matters — Improve Semantic Segmentation by Global Convolutional Network
- RepVGG: Making VGG-style ConvNets Great Again
- Accelerating Very Deep Convolutional Networks for Classification and Detection
- MegDet: A Large Mini-Batch Object Detector
- Efficient and accurate approximations of nonlinear convolutional networks
- Scaling Up Your Kernels to 31×31: Revisiting Large Kernel Design in CNNs
- Simple Baselines for Image Restoration
- Objects365: A Large-Scale, High-Quality Dataset for Object Detection
- ExFuse: Enhancing Feature Fusion for Semantic Segmentation
- Single Path One-Shot Neural Architecture Search with Uniform Sampling