no code implementations • 4 Feb 2016 • M. J. Shafiee, P. Siva, C. Scharfenberger, P. Fieguth, A. Wong
In this paper, a novel approach to visual salience detection via Neural Response Divergence (NeRD) is proposed, where synaptic portions of deep neural networks, previously trained for complex object recognition, are leveraged to compute low level cues that can be used to compute image region distinctiveness.