Authors
Jing Zhang, Deng-Ping Fan, Yuchao Dai, Saeed Anwar, Fatemeh Sadat Saleh, Tong Zhang, Nick Barnes
Publication date
2020
Conference
Proceedings of the IEEE/CVF conference on computer vision and pattern recognition
Pages
8582-8591
Description
In this paper, we propose the first framework (UCNet) to employ uncertainty for RGB-D saliency detection by learning from the data labeling process. Existing RGB-D saliency detection methods treat the saliency detection task as a point estimation problem, and produce a single saliency map following a deterministic learning pipeline. Inspired by the saliency data labeling process, we propose probabilistic RGB-D saliency detection network via conditional variational autoencoders to model human annotation uncertainty and generate multiple saliency maps for each input image by sampling in the latent space. With the proposed saliency consensus process, we are able to generate an accurate saliency map based on these multiple predictions. Quantitative and qualitative evaluations on six challenging benchmark datasets against 18 competing algorithms demonstrate the effectiveness of our approach in learning the distribution of saliency maps, leading to a new state-of-the-art in RGB-D saliency detection.
Total citations
201920202021202220232024130699510671
Scholar articles
J Zhang, DP Fan, Y Dai, S Anwar, FS Saleh, T Zhang… - Proceedings of the IEEE/CVF conference on computer …, 2020