Share Email Print

Proceedings Paper

Pixel-wise binary classification network for salient object detection
Author(s): Chuang Wu; Lihua Tian; Chen Li
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Deep convolutional neural networks have led to significant improvement over the previous salient object detection systems. The existing deep models are trained end-to-end and predicts salient objects by calculating pixel values, which results saliency maps are typically blurry. Our Pixel-wise Binary Classification Network (PBCN) focuses on binary classification in pixel level for salient object detection: saliency and background. In order to increase the resolution of output feature maps and get denser feature maps, Hybrid dilation convolution (HDC) is employed into PBCN. Then, Hybrid Dilation Spatial Pyramid Pooling (HDSPP) is proposed to extract denser multi-scale image representations. In HDSPP, it contains one 1×1 convolution and several dilated convolutions, with different rates and the output feature maps of the convolutions will be fused. Finally, softmax is introduced to implement the binary classification instead of sigmoid. Experiment, on four datasets, show that PBCN significantly improves the state-of-the-art.

Paper Details

Date Published: 15 March 2019
PDF: 8 pages
Proc. SPIE 11041, Eleventh International Conference on Machine Vision (ICMV 2018), 1104124 (15 March 2019); doi: 10.1117/12.2523113
Show Author Affiliations
Chuang Wu, Xi’an Jiaotong Univ. (China)
Lihua Tian, Xi’an Jiaotong Univ. (China)
Chen Li, Xi’an Jiaotong Univ. (China)

Published in SPIE Proceedings Vol. 11041:
Eleventh International Conference on Machine Vision (ICMV 2018)
Antanas Verikas; Dmitry P. Nikolaev; Petia Radeva; Jianhong Zhou, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?