scispace - formally typeset
Open AccessPosted Content

XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks

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

PIR-DSP: An FPGA DSP Block Architecture for Multi-precision Deep Neural Networks

TL;DR: The Precision, Interconnect, and Reuseoptimised DSP (PIR-DSP) offers a 6× improvement in multiplyaccumulate operations per DSP in the 9 × 9-bit case and decreases the run time energy to 31/19/13% of the original value in a 9/4/2-bit MobileNet-v2 DNN implementation.
Journal ArticleDOI

SparkNoC: An energy-efficiency FPGA-based accelerator using optimized lightweight CNN for edge computing

TL;DR: A lightweight neural network architecture termed as SparkNet, capable of significantly reducing the weight parameters and computation demands, and the network model of the SparkNet and the proposed accelerator architecture are both specifically built for FPGA.
Proceedings ArticleDOI

Unifying and Merging Well-trained Deep Neural Networks for Inference Stage

TL;DR: The authors aligns the layers of the original networks and merges them into a unified model by sharing the representative codes of weights and further re-train the shared weights to fine-tune the performance of the merged model.
Journal ArticleDOI

Pedestrian detection with super-resolution reconstruction for low-quality image

TL;DR: Zhang et al. as mentioned in this paper proposed a super-resolution detection (SRD) network to enhance the resolution of low-quality images that can help distinguish pedestrians from the blurred background, and adopted and improved the Faster R-CNN network to help relocate occluded pedestrians.
Proceedings ArticleDOI

A Hybrid CNN and RBF-Based SVM Approach for Breast Cancer Classification in Mammograms

TL;DR: This research focuses on the concept of transfer learning where the Convolutional Neural Network (CNN) power can be utilized as a features extractor to help with classifying benign from malignant breast cancer images.
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

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

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

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.
Related Papers (5)