Unsupervised CNN-Based Co-saliency Detection with Graphical Optimization Conference Paper uri icon

abstract

  • 2018, Springer Nature Switzerland AG. In this paper, we address co-saliency detection in a set of images jointly covering objects of a specific class by an unsupervised convolutional neural network (CNN). Our method does not require any additional training data in the form of object masks. We decompose co-saliency detection into two sub-tasks, single-image saliency detection and cross-image co-occurrence region discovery corresponding to two novel unsupervised losses, the single-image saliency (SIS) loss and the co-occurrence (COOC) loss. The two losses are modeled on a graphical model where the former and the latter act as the unary and pairwise terms, respectively. These two tasks can be jointly optimized for generating co-saliency maps of high quality. Furthermore, the quality of the generated co-saliency maps can be enhanced via two extensions: map sharpening by self-paced learning and boundary preserving by fully connected conditional random fields. Experiments show that our method achieves superior results, even outperforming many supervised methods.

published proceedings

  • COMPUTER VISION - ECCV 2018, PT V

altmetric score

  • 3

author list (cited authors)

  • Hsu, K., Tsai, C., Lin, Y., Qian, X., & Chuang, Y.

citation count

  • 43

complete list of authors

  • Hsu, Kuang-Jui||Tsai, Chung-Chi||Lin, Yen-Yu||Qian, Xiaoning||Chuang, Yung-Yu

publication date

  • January 2018