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
Compressing the CNN architecture for in-air handwritten Chinese character recognition
Ji Gan,Weiqiang Wang,Ke Lu +2 more
TL;DR: A unified algorithm to effectively compress the CNN for IAHCCR with little accuracy loss is proposed, which first utilizes the channel pruning strategy to simplify the network structure, and then adopts the network quantization technique to represent parameters with lower precision.
Proceedings ArticleDOI
ParaPIM: a parallel processing-in-memory accelerator for binary-weight deep neural networks
TL;DR: PaPIM architecture is presented, which transforms current Spin Orbit Torque Magnetic Random Access Memory sub-arrays to massively parallel computational units capable of running inferences for Binary-Weight Deep Neural Networks (BWNNs).
Journal ArticleDOI
Binarized Neural Architecture Search
TL;DR: In this paper, channel sampling and operation space reduction are introduced into a differentiable binarized neural architecture search (BNAS) to significantly reduce the cost of searching, which is accomplished through a performance-based strategy used to abandon less potential operations.
Proceedings Article
DeFINE: Deep Factorized Input Word Embeddings for Neural Sequence Modeling
TL;DR: DeFINE as mentioned in this paper uses a hierarchical structure with novel skip-connections which allows for the use of low dimensional input and output layers, reducing total parameters and training time while delivering similar or better performance versus existing methods.
Book ChapterDOI
Adaptive Computationally Efficient Network for Monocular 3D Hand Pose Estimation
Zhipeng Fan,Jun Liu,Yao Wang +2 more
TL;DR: A novel model, called Adaptive Computationally Efficient (ACE) network, is proposed, which takes advantage of a Gaussian kernel based Gate Module to dynamically switch the computation between a light model and a heavy network for feature extraction.
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.