Y
Yehui Tang
Researcher at Peking University
Publications - 42
Citations - 669
Yehui Tang is an academic researcher from Peking University. The author has contributed to research in topics: Computer science & Artificial neural network. The author has an hindex of 10, co-authored 28 publications receiving 303 citations. Previous affiliations of Yehui Tang include Huawei.
Papers
More filters
Proceedings Article
SCOP: Scientific Control for Reliable Neural Network Pruning
TL;DR: It is theoretically suggested that the knockoff condition can be approximately preserved given the information propagation of network layers, and can reduce 57.8% parameters and 60.2% FLOPs of ResNet-101 with only 0.01% top-1 accuracy loss on ImageNet.
Proceedings ArticleDOI
Manifold Regularized Dynamic Network Pruning
TL;DR: Hu et al. as mentioned in this paper proposed a new paradigm that dynamically removes redundant filters by embedding the manifold information of all instances into the space of pruned networks and aligned the manifold relationship between instances and the pruned sub-networks.
Proceedings ArticleDOI
Neuromorphic Camera Guided High Dynamic Range Imaging
TL;DR: A hybrid camera system has been built to validate that the proposed method is able to reconstruct quantitatively and qualitatively high-quality high dynamic range images by successfully fusing the images and intensity maps for various real-world scenarios.
Posted Content
ReNAS:Relativistic Evaluation of Neural Architecture Search
TL;DR: This paper proposes a relativistic architecture performance predictor in NAS (ReNAS), encoding neural architectures into feature tensors, and further refining the representations with the predictor, to determine which architecture would perform better instead of accurately predict the absolute architecture performance.
Proceedings ArticleDOI
Vision GNN: An Image is Worth Graph of Nodes
TL;DR: This paper proposes to represent the image as a graph structure and introduces a new Vision GNN (ViG) architecture to extract graphlevel feature for visual tasks, and extensive experiments on image recognition and object detection tasks demonstrate the superiority of this ViG architecture.