一句话：关注图像描述系统可能返回错误结果的问题，标题表明为其开展自动化测试。
图像描述（IC）系统自动为图像中的显著对象生成文本描述，近年来因深度神经网络的发展取得很大进步，并在科研图像标注、辅助视障人士感知世界等场景中不可或缺。然而，即便 Microsoft Azure Cognitive Services 和 IBM Image Caption Generator 等顶尖系统也可能返回错误结果，导致重要对象遗漏、严重误解乃至对人身安全的威胁。论文标题表明工作聚焦于图像描述系统的自动化测试；但给出的摘要仅阐述问题与动机，未提供具体测试方法、实现或实验评估细节。
Image captioning (IC) systems, which automatically generate a text description of the salient objects in an image (real or synthetic), have seen great progress over the past few years due to the development of deep neural networks. IC plays an indispensable role in human society, for example, labeling massive photos for scientific studies and assisting visually-impaired people in perceiving the world. However, even the top-notch IC systems, such as Microsoft Azure Cognitive Services and IBM Image Caption Generator, may return incorrect results, leading to the omission of important objects, deep misunderstanding, and threats to personal safety.
DOI 原文 ·
@inproceedings{paperbot7407,
title = {Automated testing of image captioning systems},
author = {Boxi Yu and Zhiqing Zhong and Xinran Qin and Jiayi Yao and Yuancheng Wang and Pinjia He},
booktitle = {ISSTA},
year = {2022},
doi = {10.1145/3533767.3534389}
}