Meta AI Research has recently released SAM (Segment Anything Model) which is trained on a large segmentation dataset of over 1 billion masks. As a foundation model in the field of computer vision, SAM (Segment Anything Model) has gained attention for its impressive performance in generic object segmentation. Despite its strong capability in a wide range of zero-shot transfer tasks, it remains unknown whether SAM can detect things in challenging setups like transparent objects. In this work, we perform an empirical evaluation of two glass-related challenging scenarios: mirror and transparent objects. We found that SAM often fails to detect the glass in both scenarios, which raises concern for deploying the SAM in safety-critical situations that have various forms of glass.
@article{arxiv.2305.00278,
title = {Segment Anything Model (SAM) Meets Glass: Mirror and Transparent Objects Cannot Be Easily Detected},
author = {Dongsheng Han and Chaoning Zhang and Yu Qiao and Maryam Qamar and Yuna Jung and SeungKyu Lee and Sung-Ho Bae and Choong Seon Hong},
journal= {arXiv preprint arXiv:2305.00278},
year = {2023}
}