publication . Other literature type . 2015

Figure-Ground Organization Emerges in a Deep Net with a Feedback Loop

Zipser, Karl;
Open Access
  • Published: 15 May 2015
  • Publisher: Purdue University
  • Country: United States
Abstract
We used a deep net to model how object-specific activation at the high levels of a hierarchical neural network could be fed back to modify representations at lower levels. We first identified a subset of nodes in the uppermost hidden layer that were preferentially activated by images of people. We then ran a procedure to recursively modify an image so as to increase activation of the 'person-selective' nodes. The image was modified by choosing a rectangular region (of random size and position) and reducing contrast in that region. The modification was kept if the activation of the 'person-selective’ nodes became larger relative to the activation of the remaining...
Subjects
free text keywords: Figure-Ground, Deep Net, Feedback
Related Organizations
Download from
Purdue E-Scholar
Other literature type . 2015
Powered by OpenAIRE Open Research Graph
Any information missing or wrong?Report an Issue