Papers › Non-Local Deep Features for Salient Object Detection
Non-Local Deep Features for Salient Object Detection
Zhiming Luo, Akshaya Mishra, Andrew Achkar, Justin Eichel, Shaozi Li, Pierre-Marc Jodoin
Saliency detection aims to highlight the most relevant objects in an image. Methods using conventional models struggle whenever salient objects are pictured on top of a cluttered background while deep neural nets suffer from excess complexity and slow evaluation speeds. In this paper, we propose a simplified convolutional neural network which combines local and global information through a multi-resolution 4x5 grid structure. Instead of enforcing spacial coherence with a CRF or superpixels as is usually the case, we implemented a loss function inspired by the Mumford-Shah functional which penalizes errors on the boundary. We trained our model on the MSRA-B dataset, and tested it on six different saliency benchmark datasets. Results show that our method is on par with the state-of-the-art while reducing computation time by a factor of 18 to 100 times, enabling near real-time, high performance saliency detection.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| RGB Salient Object Detection | DUTS-TE | NLDF | MAE | 0.065 | #23 of 31 | Archive leaderboard | report |
| RGB Salient Object Detection | DUTS-TE | NLDF | max F-measure | 0.816 | #23 of 31 | Archive leaderboard | report |
| RGB Salient Object Detection | ISTD | NLDF | Balanced Error Rate | 7.50 | #4 of 7 | Archive leaderboard | report |
| RGB Salient Object Detection | SBU / SBU-Refine | NLDF | Balanced Error Rate | 7.02 | #5 of 7 | Archive leaderboard | report |
| RGB Salient Object Detection | SOC | NLDF | Average MAE | 0.106 | #5 of 7 | Archive leaderboard | report |
| RGB Salient Object Detection | SOC | NLDF | S-Measure | 0.816 | #5 of 7 | Archive leaderboard | report |
| RGB Salient Object Detection | SOC | NLDF | mean E-Measure | 0.837 | #5 of 7 | Archive leaderboard | report |
| RGB Salient Object Detection | UCF | NLDF | Balanced Error Rate | 7.69 | #2 of 7 | 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.
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