NeRD: a Neural Response Divergence Approach to Visual Salience Detection
This work addresses the problem of efficient and accurate visual salience detection for computer vision applications, but it appears incremental as it builds on existing deep learning methods with a novel twist.
The paper tackled visual salience detection by proposing the Neural Response Divergence (NeRD) approach, which leverages pre-trained deep neural networks to compute low-level cues for image distinctiveness, achieving improved performance on CSSD and MSRA10k datasets with low computational complexity for near-real-time applications.
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.