UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders

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...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) s. 8579 - 8588
Hlavní autoři: Zhang, Jing, Fan, Deng-Ping, Dai, Yuchao, Anwar, Saeed, Saleh, Fatemeh Sadat, Zhang, Tong, Barnes, Nick
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.01.2020
Témata:
Labeling
Pipelines
Predictive models
Probabilistic logic
Saliency detection
Training
Uncertainty
ISSN:1063-6919
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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.
ISSN:1063-6919
DOI:10.1109/CVPR42600.2020.00861