SAM Struggles in Concealed Scenes -- Empirical Study on "Segment Anything"
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. Our main observation is that SAM looks unskilled in concealed scenes.
PDF AbstractTasks
COD10K
CAMO
NC4K
Results from the Paper
Submit
results from this paper
to get state-of-the-art GitHub badges and help the
community compare results to other papers.
