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
Sparsity-Inducing Binarized Neural Networks
TL;DR: This work proposes the Sparsity-inducing Binarized Neural Network (Si-BNN), to quantize the activations to be either 0 or +1, which introduces sparsity into binary representation, and introduces trainable thresholds into the backward function of binarization to guide the gradient propagation.
Journal ArticleDOI
Accelerating Convolutional Neural Network-Based Hyperspectral Image Classification by Step Activation Quantization
TL;DR: The newly proposed step activation quantization acceleration method is applied to a CNN for HSI with two well-known benchmark data sets and the experimental results demonstrate that the proposed method is very effective in terms of both memory savings and computation acceleration, with only a slight decrease in classification accuracy.
Journal ArticleDOI
ECG signal classification with binarized convolutional neural network.
TL;DR: This study proposes employing deep convolutional neural network (CNN)-based algorithms for real-time arrhythmia detection using a full-precision model as the teacher to regularize the training of the binarized model through knowledge distillation.
Proceedings ArticleDOI
Towards Evolutionary Compression
TL;DR: This paper presents an evolutionary method to automatically eliminate redundant convolution filters, representing each compressed network as a binary individual of specific fitness, which has the original network structure and can be directly deployed in any off-the-shelf deep learning libraries.
Book ChapterDOI
GAN Slimming: All-in-One GAN Compression by a Unified Optimization Framework
TL;DR: GAN Slimming (GS) as mentioned in this paper proposes a unified optimization framework combining multiple compression means for GAN compression, which integrates three mainstream compression techniques: model distillation, channel pruning and quantization, together with the GAN minimax objective, into one unified optimization form, that can be efficiently optimized from end to end.
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.