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
Low-Bit Quantization Needs Good Distribution
TL;DR: Scale-Clip technique is proposed, a Distribution Reshaping technique that can reshape weights or activations into a uniform-like distribution in a dynamic manner that achieves much better performance than state-of-the- art quantization methods.
Posted Content
Generalized Negative Correlation Learning for Deep Ensembling
TL;DR: A generalized bias-variance decomposition for arbitrary twice differentiable loss functions is formulated and used to derive a Generalized Negative Correlation Learning (GNCL) algorithm which offers explicit control over the ensemble's diversity and smoothly interpolates between the two extremes of independent training and the joint training of the ensemble.
Journal ArticleDOI
The Art of Getting Deep Neural Networks in Shape
TL;DR: This article focuses on tuning two important hyperparameters, depth and width, which together define the shape of the resulting network and directly affect its accuracy, speed, size, and energy consumption.
Proceedings ArticleDOI
3DICT: a reliable and QoS capable mobile process-in-memory architecture for lookup-based CNNs in 3D XPoint ReRAMs
Qian Lou,Wujie Wen,Lei Jiang +2 more
TL;DR: A 3D XPoint ReRAM-based process-in-memory architecture, 3DICT, is proposed to provide various test accuracies to applications with different priorities by lookup-based CNN tests that dynamically exploit the trade-off between test accuracy and latency.
DissertationDOI
The ZipML Framework for Training Models with End-to-End Low Precision
TL;DR: In this paper, the authors present ZipML, a framework for training machine learning models at low precision with provable guarantees, which can lead to consistent order-of-magnitude speedups.
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.