RGB Salient Object Detection
RGB Salient object detection is a task-based on a visual attention mechanism, in which algorithms aim to explore objects or regions more attentive than the surrounding areas on the scene or RGB images.
( Image credit: Attentive Feedback Network for Boundary-Aware Salient Object Detection )
Papers
Showing 1–10 of 222 papers
Benchmark Results
| # | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| 1 | CFDN | S-Measure | 0.89 | — | Unverified |
| 2 | InSPyReNet | S-Measure | 0.89 | — | Unverified |
| 3 | M3Net-S | S-Measure | 0.89 | — | Unverified |
| 4 | TRACER-TE7 | S-Measure | 0.88 | — | Unverified |
| 5 | PoolNet (VGG-16) | F-measure | 0.88 | — | Unverified |
| 6 | M3Net-R | S-Measure | 0.87 | — | Unverified |
| 7 | DSS (Res2Net-50) | F-measure | 0.84 | — | Unverified |
| 8 | HybridSOD | S-Measure | 0.83 | — | Unverified |
| 9 | CPD-R (ResNet50) | F-measure | 0.82 | — | Unverified |
| 10 | BASNet | MAE | 0.08 | — | Unverified |