NeRD: A Neural Response Divergence Approach to Visual Saliency Detection
Mohammad Javad Shafiee, Parthipan Siva, Christian Scharfenberger, Paul Fieguth, Alexander M. Wong · IEEE Signal Processing Letters · 2016
In this letter, a novel approach to visual saliency 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 saliency detection framework is proposed using deep convolutional StochasticNets. Experimental results using complex scene saliency dataset 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 attaining low computational complexity necessary for near-real-time computer vision applications.