Open AccessPosted Content
XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks
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
Posted Content
Progressive Deep Neural Networks Acceleration via Soft Filter Pruning
TL;DR: The proposed Progressive Soft Filter Pruning method prunes the network progressively and enables the pruned filters to be updated when training the model after pruning, which has three advantages over previous works: larger model capacity, less dependence on the pre-trained model and better performance.
Posted Content
Exploration of Low Numeric Precision Deep Learning Inference Using Intel FPGAs.
TL;DR: In this article, the trade-off between throughput and accuracy is discussed for different networks through various combinations of activation and weight data widths, and a hardware design for FPGAs that takes advantage of bandwidth, memory, power, and computation savings of limited numerical precision data is presented.
Journal ArticleDOI
An Approximate Memory Architecture for Energy Saving in Deep Learning Applications
TL;DR: A new memory architecture of soft approximation for deep learning applications is proposed, which reduces the refresh energy consumption while maintaining accuracy and high performance, and combines hard approximation,Which reduces the number of accesses to DRAM, with soft approximation.
Posted Content
Bi-GCN: Binary Graph Convolutional Network
TL;DR: A Binary Graph Convolutional Network (Bi-GCN), which binarizes both the network parameters and input node features, and the original matrix multiplications are revised to binary operations for accelerations.
Journal ArticleDOI
Object instance detection with pruned Alexnet and extended training data
Rui Wang,Jingwen Xu,Tony X. Han +2 more
TL;DR: Focusing on reconstructing a smaller learning network from a noted deep model, pruned Alexnet to a compressed model with fewer parameters but equivalent accuracy, denoted as BING-Pruned Alexnet(B-PA), which demonstrates that B-PA reduces the storage requirements of neural networks substantially while preserving generalization performance on object instance detection.
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.