18 citations · 37 across the 5 of their papers we have counts for
5 papers
IR2Net: Information Restriction and Information Recovery for Accurate Binary Neural Networks
Ping Xue, Yang Lu, Jingfei Chang +2
Weight and activation binarization can efficiently compress deep neural networks and accelerate model inference, but cause severe accuracy degradation. Existing optimization method…
Self-Distribution Binary Neural Networks
Ping Xue, Yang Lu, Jingfei Chang +2
In this work, we study the binary neural networks (BNNs) of which both the weights and activations are binary (i.e., 1-bit representation). Feature representation is critical for d…
UCP: Uniform Channel Pruning for Deep Convolutional Neural Networks Compression and Acceleration
Jingfei Chang, Yang Lu, Ping Xue +2
To apply deep CNNs to mobile terminals and portable devices, many scholars have recently worked on the compressing and accelerating deep convolutional neural networks. Based on thi…
Downhole Track Detection via Multiscale Conditional Generative Adversarial Nets
Jia Li, Xing Wei, Guoqiang Yang +2
Frequent mine disasters cause a large number of casualties and property losses. Autonomous driving is a fundamental measure for solving this problem, and track detection is one of…
Reinforcement Learning Based Emotional Editing Constraint Conversation Generation
Jia Li, Xiao Sun, Xing Wei +2
In recent years, the generation of conversation content based on deep neural networks has attracted many researchers. However, traditional neural language models tend to generate g…