S-SOD (Surveillance Salient Object Detection)
Introduced by Hussain et al. in Densely Deformable Efficient Salient Object Detection Network
To validate the generalization abilities of SOD models, we create a small-scale dataset by collecting the most challenging images with varying brightness and contrast, background and foreground colors overlap, among many others. We conclude that the current models, including ours, are not trust-worthy for real-world practice, demanding extensive future research for more efficient and generalized SOD models.
Papers
| Paper | Code | Results | Date | Stars |
|---|
Dataset Loaders
No data loaders found. You can
submit your data loader here.
No data loaders found. You can
submit your data loader here.
