SAM Struggles in Concealed Scenes -- Empirical Study on Segment Anything

Understand

Segmenting anything is a ground-breaking step toward artificial general intelligence, and the Segment Anything Model (SAM) greatly fosters the foundation models for computer vision.

• We could not be more excited to probe the performance traits of SAM.
• In particular, exploring situations in which SAM does not perform well is interesting.
• In this report, we choose three concealed scenes, i.e., camouflaged animals, industrial defects, and medical lesions, to evaluate SAM under unprompted settings.