Open AccessPosted Content
XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks
Reads0
Chats0
TLDR
XNOR-Nets as discussed by the authors approximate convolutions using primarily binary operations, which results in 58x faster convolutional operations and 32x memory savings, and outperforms BinaryConnect and BinaryNets by large margins on ImageNet.Abstract:
We propose two efficient approximations to standard convolutional neural networks: Binary-Weight-Networks and XNOR-Networks. In Binary-Weight-Networks, the filters are approximated with binary values resulting in 32x memory saving. In XNOR-Networks, both the filters and the input to convolutional layers are binary. XNOR-Networks approximate convolutions using primarily binary operations. This results in 58x faster convolutional operations and 32x memory savings. XNOR-Nets offer the possibility of running state-of-the-art networks on CPUs (rather than GPUs) in real-time. Our binary networks are simple, accurate, efficient, and work on challenging visual tasks. We evaluate our approach on the ImageNet classification task. The classification accuracy with a Binary-Weight-Network version of AlexNet is only 2.9% less than the full-precision AlexNet (in top-1 measure). We compare our method with recent network binarization methods, BinaryConnect and BinaryNets, and outperform these methods by large margins on ImageNet, more than 16% in top-1 accuracy.read more
Citations
More filters
Journal ArticleDOI
Stochastic Computing for Hardware Implementation of Binarized Neural Networks
Tifenn Hirtzlin,Bogdan Penkovsky,Marc Bocquet,Jacques-Olivier Klein,Jean-Michel Portal,Damien Querlioz +5 more
TL;DR: This analysis shows that the stochastic computing approach can allow considerable savings with regards to conventional binarized neural networks in terms of area and energy consumption, and that adapting them to hardware constraints can provide important benefits.
Posted Content
Deep Learning for Real-Time Crime Forecasting and its Ternarization
TL;DR: This work first presents a proper representation of crime data, then adapt the spatial temporal residual network on the well represented data to predict the distribution of crime in Los Angeles at the scale of hours in neighborhood-sized parcels, and presents a ternarization technique to address the resource consumption issue for its deployment in real world.
Posted Content
Progressive Weight Pruning Of Deep Neural Networks Using ADMM
Shaokai Ye,Tianyun Zhang,Kaiqi Zhang,Jiayu Li,Kaidi Xu,Yunfei Yang,Fuxun Yu,Jian Tang,Makan Fardad,Sijia Liu,Xiang Chen,Xue Lin,Yanzhi Wang +12 more
TL;DR: This work proposes a progressive weight pruning approach based on ADMM (Alternating Direction Method of Multipliers), a powerful technique to deal with non-convex optimization problems with potentially combinatorial constraints and achieves faster convergence and higher compression rates.
Proceedings ArticleDOI
NTIRE 2020 Challenge on Image and Video Deblurring
TL;DR: The NTIRE 2020 Challenge on Image and Video Deblurring as discussed by the authors focused on deblurring single image and video deblurings, and the winning methods demonstrate the state-of-the-art performance on image debluring tasks.
Proceedings Article
An Optimal Control Approach to Deep Learning and Applications to Discrete-Weight Neural Networks
Qianxiao Li,Shuji Hao +1 more
TL;DR: In this article, a discrete-time method of successive approximations (MSA) is proposed to train neural networks with weights that are constrained to take values in a discrete set.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.