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
Posted Content
Integer Echo State Networks: Efficient Reservoir Computing for Digital Hardware
TL;DR: The proposed intESN approach is verified with typical tasks in reservoir computing: memorizing of a sequence of inputs, classifying time series, and learning dynamic processes, and results in dramatic improvements in memory footprint and computational efficiency.
Book ChapterDOI
S2DNAS: Transforming Static CNN Model for Dynamic Inference via Neural Architecture Search
TL;DR: The authors adaptively adjusts the inference process according to each input sample, which can considerably reduce the computational cost on “easy” samples while maintaining the overall model performance, which is called dynamic inference.
Posted Content
Recent Advances in the Applications of Convolutional Neural Networks to Medical Image Contour Detection
TL;DR: This paper discusses the development of general CNNs and their applications in image contours (or edges) detection, and compares those methods in detail, to clarify their strengthens and weaknesses.
Posted Content
Quantization and Training of Low Bit-Width Convolutional Neural Networks for Object Detection
TL;DR: LBW-Net is presented, an efficient optimization based method for quantization and training of the low bit-width convolutional neural networks (CNNs) that is nearly lossless in the object detection tasks, and can even do better in some real world visual scenes.
Journal ArticleDOI
A 0.44- μ J/dec, 39.9- μ s/dec, Recurrent Attention In-Memory Processor for Keyword Spotting
TL;DR: A Recurrent Attention Model (RAM) algorithm for the KWS task (the KeyRAM algorithm) is proposed, which enables accuracy vs. energy scalability via a confidence-based computation (CC) scheme, leads to a 2.5× reduction in computational complexity compared to state-of-the-art (SOTA) neural networks, and wellsuited for in-memory computing (IMC) since the bulk of its computations are 4b matrix-vector multiplies.
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.