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
Evaluating Fault Resiliency of Compressed Deep Neural Networks
TL;DR: This work considers faults on different data types and develops a simulation framework for understanding the fault resiliency of compressed DNN models as compared to uncompressed models, and proposes software and hardware mitigation techniques to increase the fault resilience of DNN Models.
Proceedings ArticleDOI
Low Compute and Fully Parallel Computer Vision with HashMatch
Sean Fanello,Julien Valentin,Adarsh Kowdle,Christoph Rhemann,Vladimir Tankovich,Carlo Ciliberto,Philip Davidson,Shahram Izadi +7 more
TL;DR: This paper presents a new general framework for a variety of computer vision labeling tasks, called HashMatch, designed to be both fully parallel, i.e. each pixel is independently processed, and low-compute, with a model complexity an order of magnitude less than existing CNN and CRF-based approaches.
Journal ArticleDOI
LUTNet: Learning FPGA Configurations for Highly Efficient Neural Network Inference
TL;DR: LUTNet is proposed, an end-to-end hardware-software framework for the construction of area-efficient FPGA-based neural network accelerators using the native LUTs as inference operators, which facilitates smaller, less power-hungry deployment over the former while sacrificing area and energy efficiency along with throughput.
Book ChapterDOI
Neural Network Compression Framework for fast model inference
TL;DR: A new framework for neural networks compression with fine-tuning that leverages recent advances of various network compression methods and implements some of them, such as sparsity, quantization, and binarization, which can be successfully applied to a wide range of models to accelerate the inference time while keeping the original accuracy.
Posted Content
Joint Neural Architecture Search and Quantization
TL;DR: This paper integrates the tasks of architecture design and model compression into one unified framework, which enables the joint architecture search with quantization (compression) policies for neural networks.
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.