Going Deeper with Convolutions
作者： Pierre Sermanet , Christian Szegedy , Vincent Vanhoucke , Dragomir Anguelov , Yangqing Jia
DOI:
关键词: Computer science 、 Artificial intelligence 、 Hebbian theory 、 Convolutional neural network
摘要: We propose a deep convolutional neural network architecture codenamed "Inception", which was responsible for setting the new state of art classification and detection in ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC 2014). The main hallmark this is improved utilization computing resources inside network. This achieved by carefully crafted design that allows increasing depth width while keeping computational budget constant. To optimize quality, architectural decisions were based on Hebbian principle intuition multi-scale processing. One particular incarnation used our submission ILSVRC called GoogLeNet, 22 layers network, quality assessed context detection.
arxiv.org
harvard.edu参考文章(12)
Ilya Sutskever, Geoffrey Hinton, James Martens, George Dahl, On the importance of initialization and momentum in deep learning international conference on machine learning. pp. 1139- 1147 ,(2013)
Pierre Sermanet, Yann LeCun, David Eigen, Rob Fergus, Michael Mathieu, Xiang Zhang, OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks arXiv: Computer Vision and Pattern Recognition. ,(2013)
Matthew D. Zeiler, Rob Fergus, Visualizing and Understanding Convolutional Networks european conference on computer vision. pp. 818- 833 ,(2014) , 10.1007/978-3-319-10590-1_53
B. T. Polyak, A. B. Juditsky, Acceleration of stochastic approximation by averaging Siam Journal on Control and Optimization. ,vol. 30, pp. 838- 855 ,(1992) , 10.1137/0330046
Ross Girshick, Jeff Donahue, Trevor Darrell, Jitendra Malik, Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation computer vision and pattern recognition. pp. 580- 587 ,(2014) , 10.1109/CVPR.2014.81
Y. Lecun, L. Bottou, Y. Bengio, P. Haffner, Gradient-based learning applied to document recognition Proceedings of the IEEE. ,vol. 86, pp. 2278- 2324 ,(1998) , 10.1109/5.726791
Fengguang Song, Jack Dongarra, Scaling up matrix computations on shared-memory manycore systems with 1000 CPU cores international conference on supercomputing. pp. 333- 342 ,(2014) , 10.1145/2597652.2597670
Koen E. A. van de Sande, Jasper R. R. Uijlings, Theo Gevers, Arnold W. M. Smeulders, Segmentation as selective search for object recognition international conference on computer vision. pp. 1879- 1886 ,(2011) , 10.1109/ICCV.2011.6126456
Thomas Serre, Lior Wolf, Stanley Bileschi, Maximilian Riesenhuber, Tomaso Poggio, Robust Object Recognition with Cortex-Like Mechanisms IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 29, pp. 411- 426 ,(2007) , 10.1109/TPAMI.2007.56
Yann LeCun, Bernhard Boser, John S Denker, Donnie Henderson, Richard E Howard, Wayne Hubbard, Lawrence D Jackel, None, Backpropagation applied to handwritten zip code recognition Neural Computation. ,vol. 1, pp. 541- 551 ,(1989) , 10.1162/NECO.1989.1.4.541