B-AIS: An Automated Process for Black-box Evaluation of Visual Perception in AI-enabled Software against Domain Semantics
B-AIS: An Automated Process for Black-box Evaluation of Visual Perception in AI-enabled Software against Domain Semantics
复制标题
DOI：
10.1145/3551349.3561162
复制
发表时间：
2022-10
期刊：
影响因子：
--
通讯作者：
H. Barzamini;Mona Rahimi
中科院分区：
文献类型：
--
作者：
H. Barzamini;Mona Rahimi
支持AI的软件系统（AIS）在广泛的应用程序中普遍存在，例如自主系统的视觉任务，在汽车，空中和海军域中广泛部署了。被部署到关键环境中，例如公共道路例如，概念和概念变体是对自主探测器成熟的视觉感知，以识别行人的实例（汽车领域的概念）在万圣节客户中会更可靠吗？例如，以人为理解的语言显示一个概念。两者都与相互特征轮相关联，我们通过在一个称为B-AIS的框架中实施通用过程，该问题是系统地评估AIS对域的语义规格的感知，同时将其视为黑色盒子是语言中对单词的含义和理解，因此，对于人类的大脑而言，AIS像素级的视觉信息更为完整。伪像是可比的，并利用比较的结果来揭示人类可行的语言的AIS弱点。数据集中分别为45％和72％的人，用于检测行人和飞机变体的模型。
AI-enabled software systems (AIS) are prevalent in a wide range of applications, such as visual tasks of autonomous systems, extensively deployed in automotive, aerial, and naval domains. Hence, it is crucial for humans to evaluate the model’s intelligence before AIS is deployed to safety-critical environments, such as public roads. In this paper, we assess AIS visual intelligence through measuring the completeness of its perception of primary concepts in a domain and the concept variants. For instance, is the visual perception of an autonomous detector mature enough to recognize the instances of pedestrian (an automotive domain’s concept) in Halloween customes? An AIS will be more reliable once the model’s ability to perceive a concept is displayed in a human-understandable language. For instance, is the pedestrian in wheelchair mistakenly recognized as a pedestrian on bike, since the domain concepts bike and wheelchair, both associate with a mutual feature wheel? We answer the above-type questions by implementing a generic process within a framework, called B-AIS, which systematically evaluates AIS perception against the semantic specifications of a domain, while treating the model as a black-box. Semantics is the meaning and understanding of words in a language, and therefore, is more comprehensible for humans’ brains than the AIS pixel-level visual information. B-AIS processes the heterogeneous artifacts to be comparable, and leverages the comparison’s results to reveal AIS weaknesses in a human-understandable language. The evaluations of B-AIS for the two vision tasks of pedestrian and aircraft detection showed a F2 measure of 95% and 85% as well as 45% and 72% respectively in the dataset and model for the detection of pedestrian and aircraft variants.