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. Based on this concept , an efficient visual salience detection framework is proposed using deep convolutional StochasticNets. Experimental results using CSSD and MSRA10k natural image datasets show that the proposed NeRD approach can achieve improved performance when compared to state-of-the-art image saliency approaches, while the attaining low computational complexity necessary for near-real-time computer vision applications.
View on arXiv