基于成本敏感的不确定性目标检测失败识别
Cost-Sensitive Uncertainty-Based Failure Recognition for Object Detection
AI总结：
针对目标检测中的漏检和误检问题，提出成本敏感框架，利用定位偶然不确定性和softmax熵，在三个自动驾驶数据集上将失败识别率提升36-60%。
摘要：
现实应用中的目标检测器常因天气条件、输入噪声等不同因素而无法检测到目标。因此，减少错误检测的过程对安全性和准确性都至关重要。虽然基于不确定性的阈值化方法显示出潜力，但先前的研究表明不确定性与检测错误之间的相关性并不完美。这阻碍了理想的阈值化，促使我们进一步研究不同类型不确定性与检测错误之间的相关性及其相关成本。因此，我们提出了一种成本敏感的框架，该框架针对用户定义的两种错误类型（漏检和误检）的预算进行定制。我们推导了防止性能下降的最小阈值要求，并定义了评估不确定性用于失败识别适用性的指标。此外，我们自动化并优化了阈值化过程，以在指定预算下最大化失败识别率。在三个自动驾驶数据集上的评估表明，我们的方法显著提高了安全性，尤其是在具有挑战性的场景中。仅利用定位偶然不确定性和基于softmax的熵，我们的方法相比传统方法将失败识别率提升了36-60%。代码可在 https://mos-ks.github.io/publications 获取。
英文摘要：
Object detectors in real-world applications often fail to detect objects due to varying factors such as weather conditions and noisy input. Therefore, a process that mitigates false detections is crucial for both safety and accuracy. While uncertainty-based thresholding shows promise, previous works demonstrate an imperfect correlation between uncertainty and detection errors. This hinders ideal thresholding, prompting us to further investigate the correlation and associated cost with different types of uncertainty. We therefore propose a cost-sensitive framework for object detection tailored to user-defined budgets on the two types of errors, missing and false detections. We derive minimum thresholding requirements to prevent performance degradation and define metrics to assess the applicability of uncertainty for failure recognition. Furthermore, we automate and optimize the thresholding process to maximize the failure recognition rate w.r.t. the specified budget. Evaluation on three autonomous driving datasets demonstrates that our approach significantly enhances safety, particularly in challenging scenarios. Leveraging localization aleatoric uncertainty and softmax-based entropy only, our method boosts the failure recognition rate by 36-60\% compared to conventional approaches. Code is available at https://mos-ks.github.io/publications.
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。
