arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2106.02523cs.CVcs.AIcs.LG
收藏

目标检测中的幻觉现象--视觉零件验证的研究

Hallucination In Object Detection -- A Study In Visual Part Verification

Computer Vision Lab, Delft University of Technology(代尔夫特理工大学计算机视觉实验室)

Osman Semih Kayhan, Bart Vredebregt, Jan C. van Gemert

摘要:

我们表明,对象检测器可以产生幻觉,并检测丢失的对象;甚至可能准确地定位在其预期的,但不存在的位置。这对于依赖于视觉部件验证的应用程序来说尤其成问题:检测对象部件是否存在。我们展示了流行的对象检测器如何在视觉部件验证任务中产生对象幻觉,并介绍了第一个视觉部件验证数据集:DelftBikes,它有10,000张自行车照片,每张图像有22个密集注释的部件,其中一些部件可能会丢失。我们为每个部分显式地注释了一个额外的对象状态标签,以反映一个部分是丢失还是完整。我们建议评估视觉部分验证依赖于召回和比较流行的对象检测器DelftBikes。

英文摘要:

We show that object detectors can hallucinate and detect missing objects; potentially even accurately localized at their expected, but non-existing, position. This is particularly problematic for applications that rely on visual part verification: detecting if an object part is present or absent. We show how popular object detectors hallucinate objects in a visual part verification task and introduce the first visual part verification dataset: DelftBikes, which has 10,000 bike photographs, with 22 densely annotated parts per image, where some parts may be missing. We explicitly annotated an extra object state label for each part to reflect if a part is missing or intact. We propose to evaluate visual part verification by relying on recall and compare popular object detectors on DelftBikes.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑