• Publications
  • Influence
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
We introduce an extremely computation-efficient CNN architecture named ShuffleNet, which is designed specially for mobile devices with very limited computing power (e.g., 10-150 MFLOPs). The newExpand
  • 1,583
  • 279
  • PDF
ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
Currently, the neural network architecture design is mostly guided by the indirect metric of computation complexity, i.e., FLOPs. However, the direct metric, e.g., speed, also depends on the otherExpand
  • 750
  • 156
  • PDF
Channel Pruning for Accelerating Very Deep Neural Networks
  • Yihui He, X. Zhang, Jian Sun
  • Computer Science
  • IEEE International Conference on Computer Vision…
  • 19 July 2017
In this paper, we introduce a new channel pruning method to accelerate very deep convolutional neural networks. Given a trained CNN model, we propose an iterative two-step algorithm to effectivelyExpand
  • 786
  • 112
  • PDF
Large Kernel Matters — Improve Semantic Segmentation by Global Convolutional Network
One of recent trends [31, 32, 14] in network architecture design is stacking small filters (e.g., 1x1 or 3x3) in the entire network because the stacked small filters is more efficient than a largeExpand
  • 548
  • 73
  • PDF
Light-Head R-CNN: In Defense of Two-Stage Object Detector
In this paper, we first investigate why typical two-stage methods are not as fast as single-stage, fast detectors like YOLO and SSD. We find that Faster R-CNN and R-FCN perform an intensiveExpand
  • 154
  • 39
  • PDF
Single Path One-Shot Neural Architecture Search with Uniform Sampling
One-shot method is a powerful Neural Architecture Search (NAS) framework, but its training is non-trivial and it is difficult to achieve competitive results on large scale datasets like ImageNet. InExpand
  • 142
  • 28
  • PDF
CrowdHuman: A Benchmark for Detecting Human in a Crowd
Human detection has witnessed impressive progress in recent years. However, the occlusion issue of detecting human in highly crowded environments is far from solved. To make matters worse, crowdExpand
  • 67
  • 24
  • PDF
MegDet: A Large Mini-Batch Object Detector
  • Chao Peng, Tete Xiao, +5 authors Jian Sun
  • Computer Science
  • IEEE/CVF Conference on Computer Vision and…
  • 20 November 2017
The development of object detection in the era of deep learning, from R-CNN [11], Fast/Faster R-CNN [10, 31] to recent Mask R-CNN [14] and RetinaNet [24], mainly come from novel network, newExpand
  • 154
  • 18
  • PDF
DetNet: A Backbone network for Object Detection
Recent CNN based object detectors, no matter one-stage methods like YOLO, SSD, and RetinaNe or two-stage detectors like Faster R-CNN, R-FCN and FPN are usually trying to directly finetune fromExpand
  • 96
  • 16
  • PDF
MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning
  • Z. Liu, H. Mu, +4 authors Jian Sun
  • Computer Science
  • IEEE/CVF International Conference on Computer…
  • 25 March 2019
In this paper, we propose a novel meta learning approach for automatic channel pruning of very deep neural networks. We first train a PruningNet, a kind of meta network, which is able to generateExpand
  • 72
  • 16
  • PDF