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 2307.16433cs.CV
收藏

利用神经元激活模式检测分布外对象

Detecting Out-of-distribution Objects Using Neuron Activation Patterns

Warsaw University of Technology(华沙理工大学);Silesian University of Technology(西里西亚工业大学)

Bartłomiej Olber, Krystian Radlak, Krystian Chachuła, Jakub Łyskawa, Piotr Frątczak

AI总结:

针对目标检测器对分布外样本过度自信的问题,本文提出 NAPTRON,利用神经元激活模式检测 OOD 对象,并在两类场景、三种检测器上验证其优于现有方法且不损害 ID 性能,同时构建了最大的开源 OOD 目标检测基准。

摘要:

目标检测对于现代机器人应用中使用的许多感知算法至关重要。遗憾的是,现有模型都倾向于为分布外(OOD)样本分配较高的置信度分数。尽管近年来计算机视觉(CV)社区已对 OOD 检测进行了广泛研究,但大多数提出的解决方案仅适用于图像识别任务。自动驾驶中的感知等现实应用面临着远比分类更复杂的挑战。在我们的工作中,我们聚焦于普遍的目标检测领域,提出了用于目标检测中分布外样本检测的神经元激活模式(Neuron Activation PaTteRns for out-of-distribution samples detection in Object detectioN,NAPTRON)。所开展的实验表明,我们的方法优于最先进的方法,且无需影响分布内(ID)性能。通过在两种不同的 OOD 场景和三类目标检测器上评估这些方法,我们创建了最大的用于 OOD 目标检测的开源基准。

英文摘要:

Object detection is essential to many perception algorithms used in modern robotics applications. Unfortunately, the existing models share a tendency to assign high confidence scores for out-of-distribution (OOD) samples. Although OOD detection has been extensively studied in recent years by the computer vision (CV) community, most proposed solutions apply only to the image recognition task. Real-world applications such as perception in autonomous vehicles struggle with far more complex challenges than classification. In our work, we focus on the prevalent field of object detection, introducing Neuron Activation PaTteRns for out-of-distribution samples detection in Object detectioN (NAPTRON). Performed experiments show that our approach outperforms state-of-the-art methods, without the need to affect in-distribution (ID) performance. By evaluating the methods in two distinct OOD scenarios and three types of object detectors we have created the largest open-source benchmark for OOD object detection.

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。

↑