</> Code with Papers by Syntology

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

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

13 Apr 2020CVPR 2020 6arXiv:2004.05763archive 2025-07-28

Jing Zhang, Deng-Ping Fan, Yuchao Dai, Saeed Anwar, Fatemeh Sadat Saleh, Tong Zhang, Nick Barnes

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.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

JingZhang617/UCNet mentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

RGB-D Salient Object DetectionSaliency DetectionThermal Image Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
RGB-D Salient Object Detection DES UC-Net Average MAE 0.019 #8 of 13 Archive leaderboard report
RGB-D Salient Object Detection DES UC-Net S-Measure 93.4 #8 of 13 Archive leaderboard report
RGB-D Salient Object Detection LFSD UC-Net Average MAE 0.066 #4 of 8 Archive leaderboard report
RGB-D Salient Object Detection LFSD UC-Net S-Measure 86.4 #4 of 8 Archive leaderboard report
RGB-D Salient Object Detection NJU2K UC-Net Average MAE 0.043 #17 of 27 Archive leaderboard report
RGB-D Salient Object Detection NJU2K UC-Net S-Measure 89.7 #17 of 27 Archive leaderboard report
RGB-D Salient Object Detection NLPR UC-Net Average MAE 0.025 #9 of 14 Archive leaderboard report
RGB-D Salient Object Detection NLPR UC-Net S-Measure 92.0 #9 of 14 Archive leaderboard report
RGB-D Salient Object Detection SIP UC-Net Average MAE 0.051 #12 of 16 Archive leaderboard report
RGB-D Salient Object Detection SIP UC-Net S-Measure 87.5 #12 of 16 Archive leaderboard report
RGB-D Salient Object Detection STERE UC-Net Average MAE 0.039 #11 of 14 Archive leaderboard report
RGB-D Salient Object Detection STERE UC-Net S-Measure 90.3 #11 of 14 Archive leaderboard report
Thermal Image Segmentation RGB-T-Glass-Segmentation UCNet MAE 0.071 #16 of 22 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: UCNet

UCNet

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections