collaborators

7 papers

cs.CV20215 cited

Incorporating Convolution Designs into Visual Transformers

Kun Yuan, Shaopeng Guo, Ziwei Liu +3

Motivated by the success of Transformers in natural language processing (NLP) tasks, there emerge some attempts (e.g., ViT and DeiT) to apply Transformers to the vision domain. How…

cs.CV202174 cited

Learning N:M Fine-grained Structured Sparse Neural Networks From Scratch

Aojun Zhou, Yukun Ma, Junnan Zhu +5

Sparsity in Deep Neural Networks (DNNs) has been widely studied to compress and accelerate the models on resource-constrained environments. It can be generally categorized into uns…

cs.CV20201 cited

Dynamic Graph: Learning Instance-aware Connectivity for Neural Networks

Kun Yuan, Quanquan Li, Dapeng Chen +2

One practice of employing deep neural networks is to apply the same architecture to all the input instances. However, a fixed architecture may not be representative enough for data…

cs.CV2019

Scale Calibrated Training: Improving Generalization of Deep Networks via Scale-Specific Normalization

Zhuoran Yu, Aojun Zhou, Yukun Ma +3

Standard convolutional neural networks(CNNs) require consistent image resolutions in both training and testing phase. However, in practice, testing with smaller image sizes is nece…

cs.CV2019

HBONet: Harmonious Bottleneck on Two Orthogonal Dimensions

Duo Li, Aojun Zhou, Anbang Yao

MobileNets, a class of top-performing convolutional neural network architectures in terms of accuracy and efficiency trade-off, are increasingly used in many resourceaware vision a…

cs.CV2019

Deeply-supervised Knowledge Synergy

Dawei Sun, Anbang Yao, Aojun Zhou +1

Convolutional Neural Networks (CNNs) have become deeper and more complicated compared with the pioneering AlexNet. However, current prevailing training scheme follows the previous…