一句话：针对关键点检测 DNN 提出基于高维多目标搜索的自动测试套件生成方法。
关键点检测 DNN（KP-DNN）能自动检测图像中的面部或手指等关键点，在驾驶员注视检测、疲劳检测等应用中十分重要。然而，KP-DNN 会同时预测多个相互独立的关键点，每个关键点都可能在目标应用中至关重要；同时图像又会受多种因素影响而差异很大，导致测试与验证十分困难。该经验论文研究使用高维多目标搜索自动生成 KP-DNN 测试套件，以面向多个关键点同时开展测试。所给摘要仅给出研究问题与动机，未提供方法细节、实验设置或评估结果，因此无法进一步总结关键结果。
Automatically detecting the positions of key-points (e.g., facial key-points or finger key-points) in an image is an essential problem in many applications, such as driver's gaze detection and drowsiness detection in automated driving systems. With the recent advances of Deep Neural Networks (DNNs), Key-Points detection DNNs (KP-DNNs) have been increasingly employed for that purpose. Nevertheless, KP-DNN testing and validation have remained a challenging problem because KP-DNNs predict many independent key-points at the same time---where each individual key-point may be critical in the targeted application---and images can vary a great deal according to many factors.
@inproceedings{paperbot6697,
title = {Automatic test suite generation for key-points detection DNNs using many-objective search (experience paper)},
author = {Fitash Ul Haq and Donghwan Shin and Lionel C. Briand and Thomas Stifter and Jun Wang},
booktitle = {ISSTA},
year = {2021},
doi = {10.1145/3460319.3464802}
}