Indexed by:期刊论文

Date of Publication:2021-03-05

Journal:IEEE ACCESS

Volume:8

Page Number:218739-218751

ISSN No.:2169-3536

Key Words:Task analysis; Image edge detection; Feature extraction; Semantics; Object detection; Training; Saliency detection; Salient object detection; object contour detection; multi-task; transfer learning; recurrent network

Abstract:Recently, fully convolutional neural networks have been adopted for salient object detection and object contour detection, and have achieved impressive performance. Closely related contours are employed to help supervise low-level features, rather than being simultaneously trained as associated tasks as in most methods. This study proposes a coarse-to-fine architecture for a contour-aware recurrent cross constraint network (CARCCNet) for salient object detection. At the coarse stage, we design a contour-aware recurrent constraint network (CARCNet) with a recurrent structure that consists of a set of contour-aware constraint modules (CACMs), saliency-aware constraint modules (SACMs), and double supervised prediction modules (DSPMs). These modules can simultaneously generate saliency maps and contour maps and alternately constrain them at each recurrent step. In the refining stage, we propose a contour knowledge transfer residual (CKTR) module to transfer the contour knowledge from the low-level branch into the saliency features to obtain the final saliency map with complete objects and accurate contours. Our CARCCNet also finally generates the object contour map at the same time without post-processing. Extensive experiments on five saliency detection benchmark datasets demonstrate the effectiveness and robustness of the proposed method.