159 citations · 943 across the 39 of their papers we have counts for
8 papers · 1 filter
Global Sparse Momentum SGD for Pruning Very Deep Neural Networks
Xiaohan Ding, Guiguang Ding, Xiangxin Zhou +3
Deep Neural Network (DNN) is powerful but computationally expensive and memory intensive, thus impeding its practical usage on resource-constrained front-end devices. DNN pruning i…
PDANet: Polarity-consistent Deep Attention Network for Fine-grained Visual Emotion Regression
Sicheng Zhao, Zizhou Jia, Hui Chen +3
Existing methods on visual emotion analysis mainly focus on coarse-grained emotion classification, i.e. assigning an image with a dominant discrete emotion category. However, these…
ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks
Xiaohan Ding, Yuchen Guo, Guiguang Ding +1
As designing appropriate Convolutional Neural Network (CNN) architecture in the context of a given application usually involves heavy human works or numerous GPU hours, the researc…
GRN: Gated Relation Network to Enhance Convolutional Neural Network for Named Entity Recognition
Hui Chen, Zijia Lin, Guiguang Ding +3
The dominant approaches for named entity recognition (NER) mostly adopt complex recurrent neural networks (RNN), e.g., long-short-term-memory (LSTM). However, RNNs are limited by t…
Incremental Few-Shot Learning for Pedestrian Attribute Recognition
Liuyu Xiang, Xiaoming Jin, Guiguang Ding +2
Pedestrian attribute recognition has received increasing attention due to its important role in video surveillance applications. However, most existing methods are designed for a f…
Adaptive Region Embedding for Text Classification
Liuyu Xiang, Xiaoming Jin, Lan Yi +1
Deep learning models such as convolutional neural networks and recurrent networks are widely applied in text classification. In spite of their great success, most deep learning mod…
Approximated Oracle Filter Pruning for Destructive CNN Width Optimization
Xiaohan Ding, Guiguang Ding, Yuchen Guo +2
It is not easy to design and run Convolutional Neural Networks (CNNs) due to: 1) finding the optimal number of filters (i.e., the width) at each layer is tricky, given an architect…
Centripetal SGD for Pruning Very Deep Convolutional Networks with Complicated Structure
Xiaohan Ding, Guiguang Ding, Yuchen Guo +1
The redundancy is widely recognized in Convolutional Neural Networks (CNNs), which enables to remove unimportant filters from convolutional layers so as to slim the network with ac…