arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.03188cs.CVcs.AI
收藏

Situation Monitor:基于萌芽集成架构的多样性驱动零样本分布外检测用于目标检测

Situation Monitor: Diversity-Driven Zero-Shot Out-of-Distribution Detection using Budding Ensemble Architecture for Object Detection

Intel Labs(英特尔实验室);Technical University of Munich(慕尼黑工业大学)

Qutub Syed, Michael Paulitsch, Korbinian Hagn, Neslihan Kose Cihangir, Kay-Ulrich Scholl, Fabian Oboril, Gereon Hinz, Alois Knoll

AI总结:

提出 Situation Monitor,一种基于萌芽集成架构和多样性损失的零样本分布外检测方法,在减少 14% 参数的同时提升了目标检测模型的 OOD 检测性能与置信度校准。

摘要:

我们引入了 Situation Monitor,这是一种用于基于 transformer 的目标检测模型的新型零样本分布外(OOD)检测方法,旨在增强自动驾驶等安全关键型机器学习应用的可靠性。Situation Monitor 利用基于多样性的萌芽集成架构(DBEA),通过在萌芽集成架构基础上将多样性损失整合到训练过程中来提高 OOD 性能,检测 Far-OOD 样本并最小化 Near-OOD 样本上的误报。此外,利用生成的 DBEA 提高了模型的 OOD 性能并改善了置信度分数的校准,特别是在检测目标的交并比方面。与 vanilla 模型相比,DBEA 模型在可训练参数减少 14% 的情况下实现了这些进步。这标志着效率的显著提升,同时未损害模型检测 OOD 实例和准确校准置信度分数的能力。

英文摘要:

We introduce Situation Monitor, a novel zero-shot Out-of-Distribution (OOD) detection approach for transformer-based object detection models to enhance reliability in safety-critical machine learning applications such as autonomous driving. The Situation Monitor utilizes the Diversity-based Budding Ensemble Architecture (DBEA) and increases the OOD performance by integrating a diversity loss into the training process on top of the budding ensemble architecture, detecting Far-OOD samples and minimizing false positives on Near-OOD samples. Moreover, utilizing the resulting DBEA increases the model's OOD performance and improves the calibration of confidence scores, particularly concerning the intersection over union of the detected objects. The DBEA model achieves these advancements with a 14% reduction in trainable parameters compared to the vanilla model. This signifies a substantial improvement in efficiency without compromising the model's ability to detect OOD instances and calibrate the confidence scores accurately.

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。

↑