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 (DUTS, HRSOD, UHRSD) | S-Measure | 0.96 | — | Unverified |
| 2 | PDFNet (HRSOD, UHRSD) | S-Measure | 0.95 | — | Unverified |
| 3 | InSPyReNet (HRSOD, UHRSD) | S-Measure | 0.95 | — | Unverified |
| 4 | BiRefNet (DUTS, UHRSD) | S-Measure | 0.95 | — | Unverified |
| 5 | BiRefNet (HRSOD, UHRSD) | S-Measure | 0.95 | — | Unverified |
| 6 | BiRefNet (DUTS, HRSOD) | S-Measure | 0.94 | — | Unverified |
| 7 | InSPyReNet (DUTS, HRSOD) | S-Measure | 0.94 | — | Unverified |
| 8 | PGNet (HRSOD, UHRSD) | S-Measure | 0.94 | — | Unverified |
| 9 | InSPyReNet | S-Measure | 0.93 | — | Unverified |
| 10 | BiRefNet (DUTS) | S-Measure | 0.93 | — | Unverified |