基于Segment Anything模型的玻璃钢镜和透明物体难以检测

Apr, 2023

基于Segment Anything模型的玻璃钢镜和透明物体难以检测

Segment Anything Model (SAM) Meets Glass: Mirror and Transparent Objects Cannot Be Easily Detected

Dongsheng Han, Chaoning Zhang, Yu Qiao, Maryam Qamar, Yuna Jung...

TL;DRMeta AI Research发布了基于超过10亿掩模的大型分割数据集训练的SAM模型，尽管SAM在诸多领域具备强大的能力，但我们的经验评估表明该模型存在在透明物体场景中无法检测的问题。特别是在含有各种形式的玻璃的安全关键情况下，部署SAM可能存在风险。

Abstract

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, →