Speedup of deep learning ensembles for semantic segmentation using a model compression technique

Ba, 2014, Do deep nets really need to be deep?, 2654 Badrinarayanan, V., Handa, A., Cipolla, R., 2015. Segnet: a deep convolutional encoder-decoder architecture for robust semantic pixel-wise labelling. arXiv preprint arXiv:1510.07818v1. Bottou, 1994, Comparison of classifier methods: a case study in handwritten digit recognition Bucilu, 2006, Model compression, 535 Chan, 2015, Transferring knowledge from a RNN to a DNN Chen, 2015, Semantic image segmentation with deep convolutional nets and fully connected crfs Ciresan, 2012, Multi-column deep neural networks for image classification, 3642 Dahl, 2012, Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition, Trans/ Audio Speech Lang/ Process, 20, 30, 10.1109/TASL.2011.2134090 Everingham, M., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A., The PASCAL Visual Object Classes Challenge (VOC2012) 2012. Hariharan, 2011, Semantic contours from inverse detectors, 991 He, 2016, Deep residual learning for image recognition Hinton, 2012, Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups, Signal Process. Mag. IEEE, 29, 82, 10.1109/MSP.2012.2205597 Hinton, 2015, Distilling the knowledge in a neural network Krizhevsky, 2012, Imagenet classification with deep convolutional neural networks, 1097 LeCun, 1995, Comparison of learning algorithms for handwritten digit recognition, vol. 60, 53 Liu, 2009, Nonparametric scene parsing: Label transfer via dense scene alignment, 1972 Long, 2015, Fully convolutional networks for semantic segmentation, 3431 Mnih, 2013, Playing atari with deep reinforcement learning Noh, 2015, Learning deconvolution network for semantic segmentation, 1520 Papandreou, 2015 Romero, A., Ballas, N., Kahou, S.E., Chassang, A., Gatta, C., Bengio, Y., 2014. Fitnets: hints for thin deep nets. CoRR abs/1412.6550. Sermanet, 2011, Traffic sign recognition with multi-scale convolutional networks, 2809 Simonyan, K., Zisserman, A., 2014. Very deep convolutional networks for large-scale image recognition. CoRR abs/1409.1556. Szegedy, 2016, Inception-v4, inception-resnet and the impact of residual connections on learning Szegedy, 2015, Going deeper with convolutions, 1 Wu, Z., Shen, C., van den Hengel, A., 2016. High-performance semantic segmentation using very deep fully convolutional networks. CoRR abs/1604.04339. Zheng, 2015, Conditional random fields as recurrent neural networks, 1529