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
QUOTIENT: Two-Party Secure Neural Network Training and Prediction
TL;DR: In this paper, a new method for discretized training of DNNs, along with a customized secure two-party protocol for it, is presented, which incorporates key components of state-of-the-art DNN training such as layer normalization and adaptive gradient methods.
Posted Content
Rethinking floating point for deep learning.
TL;DR: This work improves floating point to be more energy efficient than equivalent bit width integer hardware on a 28 nm ASIC process while retaining accuracy in 8 bits with a novel hybrid log multiply/linear add, Kulisch accumulation and tapered encodings from Gustafson's posit format.
Posted Content
BSP-Net: Generating Compact Meshes via Binary Space Partitioning
TL;DR: BSP-Net is a network that learns to represent a 3D shape via convex decomposition, which is unsupervised since no convex shape decompositions are needed for training and the reconstruction quality is competitive with state-of-the-art methods while using much fewer primitives.
Posted Content
ATOMO: Communication-efficient Learning via Atomic Sparsification
Hongyi Wang,Scott Sievert,Zachary Charles,Shengchao Liu,Stephen J. Wright,Dimitris S. Papailiopoulos +5 more
TL;DR: ATOMO as mentioned in this paper is a general framework for atomic sparsification of stochastic gradients that can operate on any possible atomic decomposition, including element-wise, singular value, and Fourier decompositions.
Posted Content
Accelerating CNN inference on FPGAs: A Survey
TL;DR: The methods and tools investigated in this survey represent the recent trends in FPGA CNN inference accelerators and will fuel the future advances on effcient hardware deep learning.
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.