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
Target discrimination, concentration prediction, and status judgment of electronic nose system based on large-scale measurement and multi-task deep learning
Zhenhong Dai,Tao Wang,Hexin Zhang,Yu Wu,Wenkai Jiang,Xinwei Chen,Min Zeng,Jianhua Yang,Yanjie Su,Nantao Hu,Zhi Yang +10 more
TL;DR: This work shows the distinct advantages of combining “big data” and “deep learning” in the gas-sensing field and further proves that the employment of MTL-CNN can significantly improve the training and application efficiency of the E-nose.
Journal ArticleDOI
Learning Sparse Low-Precision Neural Networks With Learnable Regularization
TL;DR: In this article, a low-precision DNN compression pipeline is proposed, which combines weight pruning, quantization, and entropy coding to reduce the mismatch in the forward and backward passes.
Journal ArticleDOI
Methodologies of Compressing a Stable Performance Convolutional Neural Networks in Image Classification
TL;DR: The main goals are memory compression and complexity reduction (both operations and cycles reduction) of CNNs, using methods (including quantization and pruning) that don’t require retraining (i.e., allowing them in mobile system, or robots).
Proceedings ArticleDOI
Towards Fast and Energy-Efficient Binarized Neural Network Inference on FPGA
TL;DR: In this paper, the authors proposed two types of fast and energy-efficient architectures for BNN inference on FPGA and demonstrated that 80% of the computation and 40% of buffer access can be skipped by exploiting BNN similarity.
Proceedings ArticleDOI
An object detector based on multiscale sliding window search using a fully pipelined binarized CNN on an FPGA
TL;DR: The FPGA based object detector suitable for the embedded realtime applications, which is higher with respect to recognition accuracy, and its power consumption is lower than the GPU based YOLOv2.
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.