论文标题
基于神经网络的单眼姿势估计的在线监视
Online Monitoring for Neural Network Based Monocular Pedestrian Pose Estimation
论文作者
论文摘要
现在，几个自主管道具有依赖深度学习方法的核心组成部分。尽管这些方法在名义条件下运行良好，但它们倾向于具有出乎意料且严重的故障模式，这些模式在安全至关重要的应用中（包括自动驾驶汽车）时会引起人们的关注。有几项旨在表征网络脱机的鲁棒性的作品，但是目前缺乏在操作过程中在线监视网络输出的正确性的工具。我们研究了估计3D人类形状并从图像中构成的神经网络的在线输出监视的问题。我们的第一个贡献是为人类置换重建网络提供和评估基于模型和学习的监测器，并评估其预测给定测试输入的输出损失的能力。作为第二个贡献，我们介绍了一个受对抗训练的在线监视器（ATOM），该监视器（ATOM）学习如何有效地预测数据中的损失。 Atom主导基于模型的基线，并可以检测出不良的输出，从而导致人类姿势产出质量的实质性改善。我们的最终贡献是一项广泛的实验评估，该评估表明，原子不正确的输出丢弃的输出将平均误差提高了12.5％，而最坏的误差则提高了126.5％。
Several autonomy pipelines now have core components that rely on deep learning approaches. While these approaches work well in nominal conditions, they tend to have unexpected and severe failure modes that create concerns when used in safety-critical applications, including self-driving cars. There are several works that aim to characterize the robustness of networks offline, but currently there is a lack of tools to monitor the correctness of network outputs online during operation. We investigate the problem of online output monitoring for neural networks that estimate 3D human shapes and poses from images. Our first contribution is to present and evaluate model-based and learning-based monitors for a human-pose-and-shape reconstruction network, and assess their ability to predict the output loss for a given test input. As a second contribution, we introduce an Adversarially-Trained Online Monitor ( ATOM ) that learns how to effectively predict losses from data. ATOM dominates model-based baselines and can detect bad outputs, leading to substantial improvements in human pose output quality. Our final contribution is an extensive experimental evaluation that shows that discarding outputs flagged as incorrect by ATOM improves the average error by 12.5%, and the worst-case error by 126.5%.
