Co-Saliency Detection via Mask-Guided Fully Convolutional Networks With Multi-Scale Label Smoothing

Kaihua Zhang, Tengpeng Li, Bo Liu, Qingshan Liu; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 3095-3104

Abstract


In image co-saliency detection problem, one critical issue is how to model the concurrent pattern of the co-salient parts, which appears both within each image and across all the relevant images. In this paper, we propose a hierarchical image co-saliency detection framework as a coarse to fine strategy to capture this pattern. We first propose a mask-guided fully convolutional network structure to generate the initial co-saliency detection result. The mask is used for background removal and it is learned from the high-level feature response maps of the pre-trained VGG-net output. We next propose a multi-scale label smoothing model to further refine the detection result. The proposed model jointly optimizes the label smoothness of pixels and superpixels. Experiment results on three popular image co-saliency detection benchmark datasets including iCoseg, MSRC and Cosal2015 demonstrate the remarkable performance compared with the state-of-the-art methods.

Related Material


[pdf]
[bibtex]
@InProceedings{Zhang_2019_CVPR,
author = {Zhang, Kaihua and Li, Tengpeng and Liu, Bo and Liu, Qingshan},
title = {Co-Saliency Detection via Mask-Guided Fully Convolutional Networks With Multi-Scale Label Smoothing},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}