A multiscale dilated dense convolutional network for saliency prediction with instance-level attention competition

摘要

Data-driven saliency estimation attracts increasing interests in recent years because of the establishment of large-scale annotated datasets and the evolution of deep convolutional neural networks (CNN). Although CNN-based models perform much better than traditional ones in saliency prediction, there is still a gap between computational models and human behavior. One reason is that existing approaches fail assigning correct saliency to different objects in scenes with multiple objects. In this paper, we propose a multiscale dilated dense convolutional network to handle instance-level attention competition for better saliency prediction. In the proposed architecture, dense connections encode inter- and intra-class features for instance-level attention competition, dilated convolution collects contextual information to enrich feature representations of instances, and shortcut connections provide multiscale features for attention competition across scales. According to evaluations on three challenging datasets, CAT2000, SALICON, and MIT1003, the proposed model achieves the state-of-the-art performance. (C) 2019 Elsevier Inc. All rights reserved.