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
Posted Content
A Multi-Bit Neuromorphic Weight Cell using Ferroelectric FETs, suitable for SoC Integration
Obradovic Borna J,Titash Rakshit,Hatcher Ryan M,Kittl Jorge A,Rwik Sengupta,Hong Joon Goo,Mark S. Rodder +6 more
TL;DR: In this paper, a multi-bit digital weight cell for high-performance, inference-only non-GPU-like neuromorphic accelerators is presented, which eliminates the need for DRAM access and is purely digital.
Posted Content
The Enhanced Hybrid MobileNet.
Hong-Yen Chen,Chung-Yen Su +1 more
TL;DR: In this paper, the authors proposed two different methods to improve MobileNet, which are based on adjusting two hyper-parameters width multiplier and depth multiplier, combing max pooling or fractional Max Pooling with MobileNet.
Posted Content
Binary Neural Networks for Memory-Efficient and Effective Visual Place Recognition in Changing Environments.
TL;DR: This paper takes a multi-step approach of decreasing the precision of model parameters, combining it with network depth reduction and fewer neurons in the classifier stage to propose a new class of highly compact models that drastically reduce the memory requirements while maintaining state-of-the-art VPR performance, and can be tuned to various platforms and application scenarios.
Posted Content
Search for Better Students to Learn Distilled Knowledge
Jindong Gu,Volker Tresp +1 more
TL;DR: This work proposes to search for the optimal student automatically based on L1-norm optimization, a subgraph from the teacher network topology graph is selected as a student, the goal of which is to minimize the KL-divergence between student's and teacher's outputs.
Proceedings ArticleDOI
Synchronous Multi-GPU Deep Learning with Low-Precision Communication: An Experimental Study
TL;DR: This paper conducts an empirical study to answer the question: can low-precision communication consistently improve the end-to-end performance of training modern neural networks, with no accuracy loss?
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.