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 | BiRefNet (HRSOD, UHRSD) | S-measure | 0.98 | — | Unverified |
| 2 | BiRefNet (DUTS, HRSOD, UHRSD) | S-measure | 0.98 | — | Unverified |
| 3 | BiRefNet (DUTS, UHRSD) | S-measure | 0.98 | — | Unverified |
| 4 | BiRefNet (DUTS, HRSOD) | S-measure | 0.97 | — | Unverified |
| 5 | InSPyReNet (DUTS, HRSOD) | S-measure | 0.97 | — | Unverified |
| 6 | BiRefNet (DUTS) | S-measure | 0.97 | — | Unverified |
| 7 | InSPyReNet | S-measure | 0.96 | — | Unverified |
| 8 | PGNet (HRSOD, UHRSD) | S-measure | 0.95 | — | Unverified |
| 9 | PGNet (DUTS, HRSOD) | S-measure | 0.95 | — | Unverified |
| 10 | PGNet | S-measure | 0.94 | — | Unverified |