一句话：提出蜕变对象插入方法，为深度神经网络目标检测器提供系统化测试，以发现其错误行为。
深度神经网络目标检测器已广泛用于图像和视频中的目标识别，但与传统软件类似，仍可能产生错误，并带来自动驾驶等安全关键场景中的严重后果。然而，目前尚缺乏有原则、系统化的目标检测器测试方法。论文针对这一问题，提出蜕变对象插入（metamorphic object insertion）的测试思路：围绕对象检测系统构造蜕变关系，并通过对象插入生成测试输入，以检验模型在受控变化下输出是否保持一致或符合预期，从而暴露检测错误。标题和摘要表明其核心贡献在于为 OD 提供系统化测试手段；但所给摘要未说明具体实现细节、实验设置及定量评估结果。
Recent advances in deep neural networks (DNNs) have led to object detectors (ODs) that can rapidly process pictures or videos, and recognize the objects that they contain. Despite the promising progress by industrial manufacturers such as Amazon and Google in commercializing deep learning-based ODs as a standard computer vision service, ODs --- similar to traditional software --- may still produce incorrect results. These errors, in turn, can lead to severe negative outcomes for the users. For instance, an autonomous driving system that fails to detect pedestrians can cause accidents or even fatalities. However, despite their importance, principled, systematic methods for testing ODs do not yet exist.
DOI 原文 ·
@inproceedings{paperbot5968,
title = {Metamorphic object insertion for testing object detection systems},
author = {Shuai Wang and Zhendong Su},
booktitle = {ASE},
year = {2020},
doi = {10.1145/3324884.3416584}
}