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
Journal ArticleDOI
HFPQ: deep neural network compression by hardware-friendly pruning-quantization
Fan Yingbo,Wei Pang,ShengLi Lu +2 more
TL;DR: The hardware-friendly pruning quantization (HFPQ) method proposed in this paper trains the network after pruning and then quantizes the weights, which effectively combines layered channel pruning with quantization by a power exponential of 2.
Posted Content
ApproxNet: Content and Contention-Aware Video Analytics System for Embedded Clients
Ran Xu,Rajesh Kumar,Pengcheng Wang,Peter Bai,Ganga Meghanath,Somali Chaterji,Subrata Mitra,Saurabh Bagchi +7 more
TL;DR: ApproxNet is introduced, a video analytics system for embedded or mobile clients that enables novel dynamic approximation techniques to achieve desired inference latency and accuracy trade-off under changing runtime conditions by enabling two approximation knobs within a single DNN model.
Posted Content
Depthwise Non-local Module for Fast Salient Object Detection Using a Single Thread
TL;DR: A novel depthwise nonlocal module (DNL) is proposed, which implicitly models contrast via harvesting intrachannel and interchannel correlations in a self-attention manner and achieves competitive accuracy and high inference efficiency simultaneously with a single CPU thread.
Proceedings ArticleDOI
Training and Meta-Training Binary Neural Networks with Quantum Computing
TL;DR: It is shown that the complete loss function landscape of a neural network can be represented as the quantum state output by a quantum computer and, further, that with minor adaptation, this method can also represent the meta-loss landscapes of a number of neural network architectures simultaneously.
Posted Content
Diversifying Inference Path Selection: Moving-Mobile-Network for Landmark Recognition
TL;DR: This paper proposes a novel Moving-Mobile-Network, named M2Net, for landmark recognition, equipped each landmark image with located geographic information, and intuitively finds that M2 net can essentially promote the diversity of the inference path (selected blocks subset) selection, so as to enhance the recognition accuracy.
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.