Salient deconvolutional networks

Related work
DeConvNets最初用于非监督学习【1】【2】，后被用于可视化【3】。文章【4】基于文章【5】，文章【5】是在先前hog,sift,BoVW或其他一些神经网络表达基础上。【6】学习第二个网络用于第一个网络的inverse。【7,8,9】利用cnn的特性，生成图像confuse them。本文与【10】的工作相似。
近期DeConvNets被用于语义图像分割
[1]M. D. Zeiler, D. Krishnan, G. W. Taylor, and R. Fergus. Deconvolutional Networks. In Proc.
CVPR, 2010.
[2]M. D. Zeiler, G. W. Taylor, and R. Fergus. Adaptive Deconvolutional Networks for Mid and
High Level Feature Learning. In Proc. ICCV, 2011.
[3]M. D. Zeiler and R. Fergus. Visualizing and understanding convolutional networks. In Proc.
ECCV, 2014.
【4】J. Yosinksi, J. Clune, A. Nguyen, T. Fuchs, and H. Lipson. Understanding neural networks
through deep visualization. In ICML Deep Learning Workshop, 2015.
【5】A. Mahendran and A. Vedaldi. Understanding deep image representations by inverting them.
In Proc. CVPR, 2015.
【6】C. M. Bishop. Neural Networks for Pattern Recognition. Clarend