Salient Object Detection Driven By Fixation Prediction
Abstract
Research in visual saliency has been focused on two major types of models namely fixation prediction and salient object detection. The relationship between the two, however, has been less explored. In this paper, we propose to employ the former model type to identify and segment salient objects in scenes. We build a novel neural network called Attentive Saliency Network (ASNet)1 that learns to detect salient objects from fixation maps. The fixation map, derived at the upper network layers, captures a high-level understanding of the scene. Salient object detection is then viewed as fine-grained object-level saliency segmentation and is progressively optimized with the guidance of the fixation map in a top-down manner. ASNet is based on a hierarchy of convolutional LSTMs (convLSTMs) that offers an efficient recurrent mechanism for sequential refinement of the segmentation map. Several loss functions are introduced for boosting the performance of the ASNet. Extensive experimental evaluation shows that our proposed ASNet is capable of generating accurate segmentation maps with the help of the computed fixation map. Our work offers a deeper insight into the mechanisms of attention and narrows the gap between salient object detection and fixation prediction.
Publication Date
12-14-2018
Publication Title
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Number of Pages
1711-1720
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/CVPR.2018.00184
Copyright Status
Unknown
Socpus ID
85054839784 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/85054839784
STARS Citation
Wang, Wenguan; Shen, Jianbing; Dong, Xingping; and Borji, Ali, "Salient Object Detection Driven By Fixation Prediction" (2018). Scopus Export 2015-2019. 9456.
https://stars.library.ucf.edu/scopus2015/9456