Tunnel Effect in CNNs: Image Reconstruction From Max Switch Locations

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 508
  • Download : 0
In this letter, we show that reconstruction of an image passed through a neural network is possible, using only the locations of the max pool activations. This was demonstrated with an architecture consisting of an encoder and a decoder. The decoder is amirrored version of the encoder, where convolutions are replaced with deconvolutions and poolings are replaced with unpooling layers. The locations of the max pool switches are transmitted to the corresponding unpooling layer. The reconstruction is computed only from these switches without the use of feature values. Using only the max switch location information of the pool layers, a surprisingly good image reconstruction can be achieved. We examine this effect in various architectures, as well as how the quality of the reconstruction is affected by the number of features. We also compare the reconstruction with an encoder with randomly initialized weights with an encoder pretrained for classification. Finally, we give recommendations for future architecture decisions.
Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Issue Date
2017-03
Language
English
Article Type
Article
Citation

IEEE SIGNAL PROCESSING LETTERS, v.24, no.3, pp.254 - 258

ISSN
1070-9908
DOI
10.1109/LSP.2016.2638435
URI
http://hdl.handle.net/10203/223269
Appears in Collection
EE-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0