46 citations · 79 across the 8 of their papers we have counts for
8 papers
Persia: An Open, Hybrid System Scaling Deep Learning-based Recommenders up to 100 Trillion Parameters
Xiangru Lian, Binhang Yuan, Xuefeng Zhu +24
Deep learning based models have dominated the current landscape of production recommender systems. Furthermore, recent years have witnessed an exponential growth of the model scale…
Graph-based Visual-Semantic Entanglement Network for Zero-shot Image Recognition
Yang Hu, Guihua Wen, Adriane Chapman +5
Zero-shot learning uses semantic attributes to connect the search space of unseen objects. In recent years, although the deep convolutional network brings powerful visual modeling…
Multiple Attentional Pyramid Networks for Chinese Herbal Recognition
Yingxue Xu, Guihua Wen, Yang Hu +4
Chinese herbs play a critical role in Traditional Chinese Medicine. Due to different recognition granularity, they can be recognized accurately only by professionals with much expe…
Stochastic Region Pooling: Make Attention More Expressive
Mingnan Luo, Guihua Wen, Yang Hu +2
Global Average Pooling (GAP) is used by default on the channel-wise attention mechanism to extract channel descriptors. However, the simple global aggregation method of GAP is easy…
Inner-Imaging Networks: Put Lenses into Convolutional Structure
Yang Hu, Guihua Wen, Mingnan Luo +4
Despite the tremendous success in computer vision, deep convolutional networks suffer from serious computation costs and redundancies. Although previous works address this issue by…
Chinese Herbal Recognition based on Competitive Attentional Fusion of Multi-hierarchies Pyramid Features
Yingxue Xu, Guihua Wen, Yang Hu +3
Convolution neural netwotks (CNNs) are successfully applied in image recognition task. In this study, we explore the approach of automatic herbal recognition with CNNs and build th…
Metabolize Neural Network
Dan Dai, Zhiwen Yu, Yang Hu +2
The metabolism of cells is the most basic and important part of human function. Neural networks in deep learning stem from neuronal activity. It is self-evident that the significan…
Competitive Inner-Imaging Squeeze and Excitation for Residual Network
Yang Hu, Guihua Wen, Mingnan Luo +3
Residual networks, which use a residual unit to supplement the identity mappings, enable very deep convolutional architecture to operate well, however, the residual architecture ha…