XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks

Keywords

XNOR gate, Convolutional neural network, Binary number, Computer science, Artificial intelligence

References

• Regularization of Neural Networks using DropConnectLi Wan, Matthew D. Zeiler, Sixin Zhang — 2013
• Improving the speed of neural networks on CPUsVincent Vanhoucke, Andrew Senior, M. Mao — 2011
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick — 2015
• Merging Reality and Virtuality with Microsoft HoloLensM.L. Gottmer — 2015
• Big Neural Networks Waste CapacityYann Dauphin, Yoshua Bengio — 2013
• Training deep neural networks with low precision multiplicationsMatthieu Courbariaux, Yoshua Bengio, Jean‐Pierre David — 2014
• Fixed point optimization of deep convolutional neural networks for object recognitionSajid Anwar, Kyuyeon Hwang, Wonyong Sung — 2015
• Very Deep Convolutional Networks for Large-Scale Image RecognitionKaren Simonyan, Andrew Zisserman — 2014
• Compressing Deep Convolutional Networks using Vector QuantizationYunchao Gong, Liu Liu, Ming–Hsuan Yang — 2014
• BinaryConnect: Training Deep Neural Networks with binary weights during propagationsMatthieu Courbariaux, Yoshua Bengio, Jean‐Pierre David — 2015
• Fully convolutional networks for semantic segmentationJonathan Long, Evan Shelhamer, Trevor Darrell — 2014
• Speeding up Convolutional Neural Networks with Low Rank ExpansionsMax Jaderberg, Andrea Vedaldi, Andrew Zisserman — 2014
• Fixed-point feedforward deep neural network design using weights +1, 0, and −1Kyuyeon Hwang, Wonyong Sung — 2014
• Going deeper with convolutionsChristian Szegedy, Wei Liu, Yangqing Jia — 2014
• Rich Feature Hierarchies for Accurate Object Detection and Semantic SegmentationRoss Girshick, Jeff Donahue, Trevor Darrell — 2013
• Approximation by superpositions of a sigmoidal functionGeorge Cybenko — 1989
• Optimal Brain DamageYann LeCun, John S. Denker, Sara A. Solla — 1989
• Comparing Biases for Minimal Network Construction with Back-PropagationStephen José Hanson, Lorien Pratt — 1988
• Second Order Derivatives for Network Pruning: Optimal Brain SurgeonBabak Hassibi, David G. Stork — 1992
• Predicting Parameters in Deep LearningShakibi, Babak — 2013

Cited by

• Mining Mid-level Visual Patterns with Deep CNN ActivationsLi Yao, Lingqiao Liu, Chunhua Shen — 2015
• Quantized Convolutional Neural Networks for Mobile DevicesJiaxiang Wu, Cong Leng, Yuhang Wang — 2015
• Computational Cost Reduction in Learned Transform ClassificationsEmerson Lopes Machado, Cristiano Jacques Miosso, Ricardo von Borries — 2015
• Fixed Point Quantization of Deep Convolutional NetworksDarryl Dexu Lin, Sachin S. Talathi, V. Sreekanth Annapureddy — 2015
• High Performance Binarized Neural Networks trained on the ImageNet Classification TaskXundong Wu — 2016
• Hardware-oriented Approximation of Convolutional Neural NetworksPhilipp Gysel, Mohammad Motamedi, Soheil Ghiasi — 2016
• Ristretto: Hardware-Oriented Approximation of Convolutional Neural NetworksPhilipp Gysel — 2016
• Ternary Weight NetworksFengfu Li, Bin Liu, Wang, Xiaoxing — 2016
• Structured Convolution Matrices for Energy-efficient Deep learningRathinakumar Appuswamy, Tapan K. Nayak, John V. Arthur — 2016
• Deep neural networks are robust to weight binarization and other non-linear distortionsPaul Merolla, Rathinakumar Appuswamy, John V. Arthur — 2016
• YodaNN: An Ultra-Low Power Convolutional Neural Network Accelerator Based on Binary WeightsRenzo Andri, Lukas Cavigelli, Davide Rossi — 2016
• MCDNN: An Approximation-Based Execution Framework for Deep Stream Processing Under Resource ConstraintsSeungyeop Han, Haichen Shen, Matthai Philipose — 2016
• Understanding the Energy and Precision Requirements for Online LearningCharbel Sakr, Ameya D. Patil, Sai Zhang — 2016
• DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth GradientsShuchang Zhou, Yuxin Wu, Zekun Ni — 2016
• Local Feature Detectors, Descriptors, and Image Representations: A SurveyYusuke Uchida — 2016
• Dissecting Xeon + FPGA: Why the integration of CPUs and FPGAs makes a power difference for the datacenter: Invited PaperHerman Schmit, Randy Huang — 2016
• Face Recognition Based on Embedded SystemsHanna Bara Björgvinsdottir, Robin Seibold — 2016
• Recurrent Neural Networks With Limited Numerical PrecisionJ. C. Ott, Zhouhan Lin, Ying Zhang — 2016
• Ternary neural networks for resource-efficient AI applicationsHande Alemdar, Vincent Leroy, Adrien Prost-Boucle — 2016
• Local Binary Convolutional Neural NetworksFelix Juefei-Xu, Vishnu Naresh Boddeti, Marios Savvides — 2016

Related papers

• Learning Multiple Layers of Features from Tiny ImagesAlex Krizhevsky — 2024
• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision ApplicationsAndrew Howard, Menglong Zhu, Bo Chen — 2017
• DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth GradientsShuchang Zhou, Yuxin Wu, Zekun Ni — 2016
• Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1Matthieu Courbariaux, Itay Hubara, Daniel Soudry — 2016
• SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1MB model sizeForrest Iandola, Song Han, Matthew W. Moskewicz — 2016
• Deep Residual Learning for Image RecognitionKaiming He, Xiangyu Zhang, Shaoqing Ren — 2015
• ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton — 2012
• ImageNet Large Scale Visual Recognition ChallengeOlga Russakovsky, Jia Deng, Hao Su — 2014