Data-dependent initializations of convolutional neural networks

4th International Conference on Learning Representations, ICLR 2016 - Conference Track Proceedings

Volumn , Issue , 2016, Pages

  Krähenbühl, Philipp ^a   Doersch, Carl ^a,b   Donahue, Jeff ^a   Darrell, Trevor ^a  

^a UNIVERSITY OF CALIFORNIA   (United States)

^b Carnegie Mellon University   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

CONVOLUTION; NEURAL NETWORKS; OBJECT DETECTION; VISION;

CONVERGENCE PROPERTIES; CONVOLUTIONAL NEURAL NETWORK; DATA DEPENDENT; INITIAL WEIGHTS; INITIALIZATION PROCEDURES; SPECIFIC TASKS; STATE OF THE ART; THREE ORDERS OF MAGNITUDE;

COMPUTER VISION;

EID: 85083952350     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (14)

1. Agrawal, Pulkit, Carreira, Joao, and Malik, Jitendra. Learning to see by moving. ICCV, 2015. 7, 8
2. Bradley, David M. Learning in modular systems. Technical report, DTIC Document, 2010. 2
3. Coates, Adam and Ng, Andrew Y. Learning feature representations with k-means. In Neural Networks: Tricks of the Trade, pp. 561–580. Springer, 2012. 5
4. Doersch, Carl, Gupta, Abhinav, and Efros, Alexei A. Unsupervised visual representation learning by context prediction. ICCV, 2015. 6, 8, 11
5. Everingham, Mark, Eslami, SM Ali, Van Gool, Luc, Williams, Christopher KI, Winn, John, and Zisserman, Andrew. The Pascal Visual Object Classes challenge: A retrospective. IJCV, 111(1): 98–136, 2014. 5, 6
6. Girshick, Ross. Fast R-CNN. ICCV, 2015. 1, 6
7. Glorot, Xavier and Bengio, Yoshua. Understanding the difficulty of training deep feedforward neural networks. In AISTATS, pp. 249–256, 2010. 2, 7, 8, 9
8. He, Kaiming, Zhang, Xiangyu, Ren, Shaoqing, and Sun, Jian. Delving deep into rectifiers: Surpassing human-level performance on ImageNet classification. In ICCV, 2015. 2, 7, 8, 12
9. Ioffe, Sergey and Szegedy, Christian. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In ICML, 2015. 2, 7
10. Jia, Yangqing, Shelhamer, Evan, Donahue, Jeff, Karayev, Sergey, Long, Jonathan, Girshick, Ross B., Guadarrama, Sergio, and Darrell, Trevor. Caffe: Convolutional architecture for fast feature embedding. In ACM Multimedia, MM, 2014. 5, 6, 7, 9, 12
11. Kingma, Diederik and Ba, Jimmy. Adam: A method for stochastic optimization. ICLR, 2015. 7
12. Krizhevsky, Alex, Sutskever, Ilya, and Hinton, Geoffrey E. ImageNet classification with deep convolutional neural networks. In NIPS, 2012. 2, 6, 8
13. LeCun, Y., Bottou, L., Orr, G., and Muller, K. Efficient backprop. In Neural Networks: Tricks of the trade. Springer, 1998. 2, 3
14. Russakovsky, Olga, Deng, Jia, Su, Hao, Krause, Jonathan, Satheesh, Sanjeev, Ma, Sean, Huang, Zhiheng, Karpathy, Andrej, Khosla, Aditya, Bernstein, Michael, Berg, Alexander C., and Fei-Fei, Li. ImageNet large scale visual recognition challenge. IJCV, 2015. 1