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
Proceedings ArticleDOI
NID: processing binary convolutional neural network in commodity DRAM
TL;DR: A novel processing in-DRAM framework for binary CNN, called NID, where dominant convolution operations are processed using in- DRAM bulk bitwise operations, and partial sum accumulations and tasks of the other layers such as max-pooling and normalization layers are processed in the peripheral area of DRAM with negligible overheads.
Journal ArticleDOI
Ensemble Learning of Lightweight Deep Learning Models Using Knowledge Distillation for Image Classification
Jaeyong Kang,Jeonghwan Gwak +1 more
TL;DR: Experimental results demonstrate that the proposed ensemble model outperforms other knowledge distillation models as well as the large teacher model for image classification tasks, with less computational power than the teacher model.
Proceedings ArticleDOI
Enhanced Bayesian Compression via Deep Reinforcement Learning
TL;DR: Different from most existing network quantization methods, the EBC does not require re-training procedures after the quantization and obtains low-bit precision with acceptable accuracy drop on MNIST, CIFAR and ImageNet.
Patent
Iris boundary estimation using cornea curvature
TL;DR: In this article, the limbic boundary of an iris was determined from the corneal bulge using a head mounted display (HMD) and a processor that analyzes the eye images.
Journal ArticleDOI
Efficient Layout Hotspot Detection via Binarized Residual Neural Network Ensemble
TL;DR: A new deep learning architecture based on BNNs to speed up the neural networks in hotspot detection and shows that the architecture outperforms previous hotspot detectors in detecting accuracy and has an $8\times $ speedup over the best deep learning-based solution.
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.