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
Journal ArticleDOI
Implementation of deep-learning algorithm for obstacle detection and collision avoidance for robotic harvester
TL;DR: It is shown that the pruned model can be used for obstacle detection and collision avoidance in robotic harvesters and when the compaction ratio is less than 80%, a more efficient model with a slightly reduced accuracy in comparison to the original model was achieved.
Journal ArticleDOI
Survey on decentralized congestion control methods for vehicular communication
Ali Balador,Elena Cinque,M. Pratesi,Francesco Valentini,Chumeng Bai,Arrate Alonso Gómez,Mahboubeh Mohammadi +6 more
TL;DR: A review of the DCC standardization activities is proposed as well as an analysis of the existing methods and algorithms for the congestion mitigation, and some applied machine learning techniques for DCC are addressed.
Journal ArticleDOI
Binary neural networks for speech recognition
Yanmin Qian,Xu Xiang +1 more
TL;DR: In this work, binary neural networks for speech recognition are developed to reduce the computational cost during the inference stage, and a fast implementation of binary matrix multiplication is introduced.
Journal ArticleDOI
Design of MTJ-Based nonvolatile logic gates for quantized neural networks
TL;DR: The impact of the proposed nonvolatile logic gates for binary and ternary neural networks on energy consumption, delay, and area overhead reduction is demonstrated through circuit evaluations based on the parameters of the measured MTJ devices.
Posted Content
Building Efficient CNN Architecture for Offline Handwritten Chinese Character Recognition
TL;DR: Wang et al. as discussed by the authors proposed a novel technique called Global Weighted Arverage Pooling for reducing the parameters in fully connected layer without loss in accuracy, and implemented a cascaded model in single CNN by adding mid output layer to complete recognition as early as possible, which reduces average inference time significantly.
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.