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
In-network Neural Networks.
TL;DR: N2Net, a system that implements binary neural networks using commodity switching chips deployed in network switches and routers, shows that these devices can run simple neural network models at packet processing speeds of billions of packets per second.
Proceedings ArticleDOI
Optimize Deep Convolutional Neural Network with Ternarized Weights and High Accuracy
TL;DR: Li et al. as mentioned in this paper proposed statistical weight scaling and residual expansion methods to reduce the bit-width of the whole network weight parameters to ternary values (i.e. −1, 0, +1), with the objectives to greatly reduce model size, computation cost and accuracy degradation caused by the model compression.
Posted Content
REQ-YOLO: A Resource-Aware, Efficient Quantization Framework for Object Detection on FPGAs
TL;DR: In this article, a resource-aware, systematic weight quantization framework for object detection is proposed, considering both algorithm and hardware resource aspects in object detection. But it suffers from non-negligible accuracy loss and underutilized digital signal processing (DSP) blocks of FPGAs.
Posted Content
Not All Ops Are Created Equal
TL;DR: It is shown that throughput and energy varies by up to 5X across different neural network operation types on an off-the-shelf Arm Cortex-M7 microcontroller, and memory required for activation data also need to be considered, apart from the model parameters, for network architecture exploration studies.
Proceedings ArticleDOI
Efficient Interaction-based Neural Ranking with Locality Sensitive Hashing
Shiyu Ji,Jinjin Shao,Tao Yang +2 more
TL;DR: This paper investigates fast approximation of three interaction-based neural ranking algorithms using Locality Sensitive Hashing (LSH), which accelerates query-document interaction computation by using a runtime cache with precomputed term vectors, and speeds up kernel calculation by taking advantages of limited integer similarity values.
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.