Denoising autoencoder with modulated lateral connections learns invariant representations of natural images

Antti Rasmus, Tapani Raiko, Harri Valpola

Research output: Contribution to conferencePaperScientificpeer-review

Abstract

Suitable lateral connections between encoder and decoder are shown to allow higher layers of a denoising autoencoder (dAE) to focus on invariant representations. In regular autoencoders, detailed information needs to be carried through the highest layers but lateral connections from encoder to decoder relieve this pressure. It is shown that abstract invariant features can be translated to detailed reconstructions when invariant features are allowed to modulate the strength of the lateral connection. Three dAE structures with modulated and additive lateral connections, and without lateral connections were compared in experiments using real-world images. The experiments verify that adding modulated lateral connections to the model 1) improves the accuracy of the probability model for inputs, as measured by denoising performance; 2) results in representations whose degree of invariance grows faster towards the higher layers; and 3) supports the formation of diverse invariant poolings.

Original languageEnglish
Publication statusPublished - 1 Jan 2015
MoE publication typeNot Eligible
EventInternational Conference on Learning Representations - San Diego, United States
Duration: 7 May 20159 May 2015
Conference number: 3

Conference

ConferenceInternational Conference on Learning Representations
Abbreviated titleICLR
Country/TerritoryUnited States
CitySan Diego
Period07/05/201509/05/2015

Fingerprint

Dive into the research topics of 'Denoising autoencoder with modulated lateral connections learns invariant representations of natural images'. Together they form a unique fingerprint.

Cite this