M
Mingqing Xiao
Researcher at Peking University
Publications - 19
Citations - 277
Mingqing Xiao is an academic researcher from Peking University. The author has contributed to research in topics: Computer science & Medicine. The author has an hindex of 5, co-authored 7 publications receiving 78 citations. Previous affiliations of Mingqing Xiao include Microsoft.
Papers
More filters
Book ChapterDOI
Invertible Image Rescaling
Mingqing Xiao,Shuxin Zheng,Chang Liu,Yaolong Wang,Di He,Guolin Ke,Jiang Bian,Zhouchen Lin,Tie-Yan Liu +8 more
TL;DR: An Invertible Rescaling Net (IRN) is developed with deliberately designed framework and objectives to produce visually-pleasing low-resolution images and meanwhile capture the distribution of the lost information using a latent variable following a specified distribution in the downscaling process.
Posted Content
Invertible Image Rescaling
Mingqing Xiao,Shuxin Zheng,Chang Liu,Yaolong Wang,Di He,Guolin Ke,Jiang Bian,Zhouchen Lin,Tie-Yan Liu +8 more
TL;DR: Wang et al. as discussed by the authors developed an Invertible Rescaling Net (IRN) with deliberately designed framework and objectives to produce visually-pleasing low-resolution images and meanwhile capture the distribution of the lost information using a latent variable following a specified distribution in the downscaling process.
Proceedings ArticleDOI
Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Representation
TL;DR: The proposed Differentiation on Spike Representation (DSR) method can achieve state-of-the-art SNN performance with low latency on both static and neuromorphic datasets, including CIFar-10, CIFAR-100, ImageNet, and DVS-CIFAR10.
Posted Content
TDAPNet: Prototype Network with Recurrent Top-Down Attention for Robust Object Classification under Partial Occlusion
TL;DR: This work integrates inductive priors including prototypes, partial matching and top-down modulation into deep neural networks to realize robust object classification under novel occlusion conditions, with limited Occlusion in training data.
Journal ArticleDOI
Training Neural Networks by Lifted Proximal Operator Machines.
TL;DR: The lifted proximal operator machine (LPOM) as mentioned in this paper was proposed to train fully-connected feed-forward neural networks, which is block multi-convex in all layer-wise weights and activations.