Delving into salient object subitizing and detection

• Main Authors: HE, Shengfeng, JIAO, Jianbo, ZHANG, Xiaodan, HAN, Guoqiang, LAU, Rynson W.H
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2017
• Subjects: Computer vision; Deep neural networks; Object recognition; Adaptive weights; False positive; Human visual system; Joint network; Numerical representation; Salient object detection; Salient objects; Spatial representations; Object detection; Databases and Information Systems
• Online Access: https://ink.library.smu.edu.sg/sis_research/8424; https://ink.library.smu.edu.sg/context/sis_research/article/9427/viewcontent/He_Delving_Into_Salient_ICCV_2017_paper.pdf
• Institution: Singapore Management University

Subitizing (i.e., instant judgement on the number) and detection of salient objects are human inborn abilities. These two tasks influence each other in the human visual system. In this paper, we delve into the complementarity of these two tasks. We propose a multi-task deep neural network with weight prediction for salient object detection, where the parameters of an adaptive weight layer are dynamically determined by an auxiliary subitizing network. The numerical representation of salient objects is therefore embedded into the spatial representation. The proposed joint network can be trained end-to-end using backpropagation. Experiments show the proposed multi-task network outperforms existing multi-task architectures, and the auxiliary subitizing network provides strong guidance to salient object detection by reducing false positives and producing coherent saliency maps. Moreover, the proposed method is an unconstrained method able to handle images with/without salient objects. Finally, we show state-of-theart performance on different salient object datasets.