arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2404.07045cs.CV
收藏

通过受控场景生成识别细粒度系统性错误

Identification of Fine-grained Systematic Errors via Controlled Scene Generation

Bosch Center for Artificial Intelligence, Robert Bosch GmbH(罗伯特·博世有限公司人工智能中心);University of Tübingen(蒂宾根大学)

Valentyn Boreiko, Matthias Hein, Jan Hendrik Metzen

AI总结:

本文提出 BEV2EGO 受控合成场景生成流程与配套基准,通过 BEV 到 EGO 的道路条件控制生成复杂场景,以识别检测器的细粒度系统性错误并比较多种 SOTA 模型。

摘要:

许多安全关键应用,尤其是自动驾驶,需要可靠的目标检测器。在这些检测器部署之前,一种搜索并识别潜在故障和系统性错误的方法可以非常有效地为其提供辅助。系统性错误由目标位置、尺度、朝向和颜色等属性组合,以及各自背景的构成所表征。要识别这些错误,不能依赖测试集中的真实图像,因为这些图像无法涵盖非常罕见但可能出现的属性组合。为克服这一局限,我们提出了一种用于生成具有细粒度控制的逼真合成场景的流程,能够创建包含多个目标的复杂场景。我们的方法 BEV2EGO 可逼真生成完整场景,并提供依赖道路的控制,将二维鸟瞰图(BEV)场景配置映射为第一人称视角(EGO)。此外,我们提出了一个受控场景生成基准,用于为 BEV2EGO 选择最合适的生成式外扩模型。我们进一步利用该基准对多个最先进的目标检测模型进行系统分析,并发现它们之间的差异。

英文摘要:

Many safety-critical applications, especially in autonomous driving, require reliable object detectors. They can be very effectively assisted by a method to search for and identify potential failures and systematic errors before these detectors are deployed. Systematic errors are characterized by combinations of attributes such as object location, scale, orientation, and color, as well as the composition of their respective backgrounds. To identify them, one must rely on something other than real images from a test set because they do not account for very rare but possible combinations of attributes. To overcome this limitation, we propose a pipeline for generating realistic synthetic scenes with fine-grained control, allowing the creation of complex scenes with multiple objects. Our approach, BEV2EGO, allows for a realistic generation of the complete scene with road-contingent control that maps 2D bird's-eye view (BEV) scene configurations to a first-person view (EGO). In addition, we propose a benchmark for controlled scene generation to select the most appropriate generative outpainting model for BEV2EGO. We further use it to perform a systematic analysis of multiple state-of-the-art object detection models and discover differences between them.

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。

↑