Journal
COMPUTER VISION - ECCV 2016, PT VI
Volume 9910, Issue -, Pages 120-135Publisher
SPRINGER INTERNATIONAL PUBLISHING AG
DOI: 10.1007/978-3-319-46466-4_8
Keywords
DeConvNets; Deep convolutional neural networks; Saliency; Segmentation
Ask authors/readers for more resources
Deconvolution is a popular method for visualizing deep convolutional neural networks; however, due to their heuristic nature, the meaning of deconvolutional visualizations is not entirely clear. In this paper, we introduce a family of reversed networks that generalizes and relates deconvolution, backpropagation and network saliency. We use this construction to thoroughly investigate and compare these methods in terms of quality and meaning of the produced images, and of what architectural choices are important in determining these properties. We also show an application of these generalized deconvolutional networks to weakly-supervised foreground object segmentation.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available