no code implementations • 28 Feb 2024 • Kanyifeechukwu J. Oguine, Roger D. Soberanis-Mukul, Nathan Drenkow, Mathias Unberath
We argue that SAM drastically over-segment images with high corruption levels, resulting in degraded performance when only a single segmentation mask is considered, while the combination of the masks overlapping the object of interest generates an accurate prediction.