Model Zoo :giraffe:
January 29, 2024 ยท View on GitHub
Pre-trained Checkpoints
:label: Note: If you want to try our trained checkpoints below, please make sure to locate latest.pth file to the Test.Checkpoint.checkpoint_dir.
Trained with LR dataset only (DUTS-TR, 384 X 384)
| Backbone | Train DB | Config | OneDrive | GDrive |
|---|---|---|---|---|
| Res2Net50 | DUTS-TR | InSPyReNet_Res2Net50 | Link | Link |
| SwinB | DUTS-TR | InSPyReNet_SwinB | Link | Link |
Trained with LR+HR dataset (with LR scale 384 X 384)
| Backbone | Train DB | Config | OneDrive | GDrive |
|---|---|---|---|---|
| SwinB | DUTS-TR, HRSOD-TR | InSPyReNet_SwinB_DH_LR | Link | Link |
| SwinB | HRSOD-TR, UHRSD-TR | InSPyReNet_SwinB_HU_LR | Link | Link |
| SwinB | DUTS-TR, HRSOD-TR, UHRSD-TR | InSPyReNet_SwinB_DHU_LR | Link | Link |
Trained with LR+HR dataset (with HR scale 1024 X 1024)
| Backbone | Train DB | Config | OneDrive | GDrive |
|---|---|---|---|---|
| SwinB | DUTS-TR, HRSOD-TR | InSPyReNet_SwinB_DH | Link | Link |
| SwinB | HRSOD-TR, UHRSD-TR | InSPyReNet_SwinB_HU | Link | Link |
Trained with Dichotomous Image Segmentation dataset (DIS5K-TR) with LR (384 X 384) and HR (1024 X 1024) scale
| Backbone | Train DB | Config | OneDrive | GDrive |
|---|---|---|---|---|
| SwinB | DIS5K-TR | InSPyReNet_SwinB_DIS5K_LR | Link | Link |
| SwinB | DIS5K-TR | InSPyReNet_SwinB_DIS5K | Link | Link |
Trained with Massive SOD Datasets (with LR (384 X 384) and HR (1024 X 1024), Not in the paper, for real-world scenarios)
| Backbone | Train DB | Config | OneDrive | GDrive |
|---|---|---|---|---|
| SwinB | DUTS-TR, HRSOD-TR, UHRSD-TR, DIS-TR, DUTS-TE, DUT-OMRON, ECSSD,HKU-IS, PASCAL-S, DAVIS-S, HRSOD-TE,UHRSD-TE, FSS-1000, MSRA-10K, DIS-VD, DIS-TE1, DIS-TE2, DIS-TE3, DIS-TE4 | Plus_Ultra_LR | Link | Link |
| SwinB | DUTS-TR, HRSOD-TR, UHRSD-TR, DIS-TR, DUTS-TE, DUT-OMRON, ECSSD,HKU-IS, PASCAL-S, DAVIS-S, HRSOD-TE,UHRSD-TE, FSS-1000, MSRA-10K, DIS-VD, DIS-TE1, DIS-TE2, DIS-TE3, DIS-TE4 | Plus_Ultra | Link | Link |
- We used above checkpoints for
transparent-backgroundwhich is a cool background removing command-line tool / python API!
Pre-Computed Saliency Maps
Salient Object Detection benchmarks
DIS5K Results
| Config | DIS-VD | DIS-TE1 | DIS-TE2 | DIS-TE3 | DIS-TE4 |
|---|---|---|---|---|---|
| InSPyReNet_SwinB_DIS5K_LR | Link | Link | Link | Link | Link |
| InSPyReNet_SwinB_DIS5K | Link | Link | Link | Link | Link |