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 Article
Mainstream: dynamic stem-sharing for multi-tenant video processing
Angela H. Jiang,Daniel Lin-Kit Wong,Christopher Canel,Lilia Tang,Ishan Misra,Michael Kaminsky,Michael Kozuch,Padmanabhan Pillai,David G. Andersen,Gregory R. Ganger +9 more
TL;DR: Mainstream is a new video analysis system that jointly adapts concurrent applications sharing fixed edge resources to maximize aggregate result quality and improves mean event detection F1-scores by up to 47% relative to a static approach of retraining only the last DNN layer and sharing all others.
Posted Content
Recurrent Neural Networks With Limited Numerical Precision
TL;DR: This paper addresses the question of how to best reduce weight precision during training in the case of RNNs by presenting results from the use of different stochastic and deterministic reduced precision training methods applied to three major RNN types which are then tested on several datasets.
Posted Content
COVID-MobileXpert: On-Device COVID-19 Screening using Snapshots of Chest X-Ray
Xin Li,Chengyin Li,Dongxiao Zhu +2 more
TL;DR: COVID-MobileXpert is presented: a lightweight deep neural network (DNN) based mobile app that can use noisy snapshots of chest X-ray (CXR) for point-of-care COVID-19 screening, and employs novel loss functions and training schemes for the MS network to learn the robust imaging features for accurate on-device COIDs19 screening.
Posted Content
DIET-SNN: Direct Input Encoding With Leakage and Threshold Optimization in Deep Spiking Neural Networks.
Nitin Rathi,Kaushik Roy +1 more
TL;DR: DIET-SNN is proposed, a low latency deep spiking network that is trained with gradient descent to optimize the membrane leak and the firing threshold along with other network parameters (weights) and performs 5-100X faster inference compared to other state-of-the-art SNN models.
Journal ArticleDOI
Automatic defect detection of metro tunnel surfaces using a vision-based inspection system
TL;DR: This work designs an automatic Metro Tunnel Surface Inspection System (MTSIS) for the efficient and accurate defect detection, and proposes a multi-layer feature fusion network, based on the Faster Region-based Convolutional Neural Network (Faster RCNN).
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.