Attention-aware concentrated network for saliency prediction

This paper presents a biologically-inspired saliency prediction method to imitate two main characteristics of the human perception process: focalization and orienting. The proposed network, named ACNet is composed of two modules. The first one is an essential concentrated module (CM), which assists the network to see images with appropriate receptive fields by perceiving rich multi-scale multi-receptive-field contexts of high-level features. The second is a parallel attention module (PAM), which explicitly guides the network to learn what and where is salient by simultaneously capturing global and local information with channel-wise and spatial attention mechanisms. These two modules compose the core component of the proposed method, named ACBlock, which is cascaded to progressively refine the inference of saliency estimation in a manner similar to that humans zoom in their lens to focus on the saliency. Experimental results on seven public datasets demonstrate that the proposed ACNet outperforms the state-of-the-art models without any prior knowledge or post-processing. (C) 2020 Elsevier B.V. All rights reserved.

Automated summary

This paper presents a biologically-inspired saliency prediction method that imitates two main characteristics of the human perception process: focalization and orienting. The proposed ACNet consists of two modules, a concentrated module (CM) and a parallel attention module (PAM), which together form the core component ACBlock for progressively refining saliency estimation. Experimental results show that ACNet outperforms state-of-the-art models without prior knowledge or post-processing.