SimAug: Learning Robust Representations from Simulation for Trajectory Prediction-猫眼课题宝

DOI：

10.1007/978-3-030-58601-0_17

发表时间：

2020-04

期刊：

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Junwei Liang;Lu Jiang;A. Hauptmann

本文研究了在新的场景和视角下，在看不见的摄像机中预测人的未来轨迹的问题。我们通过无真实数据的设置来解决这个问题，在这种设置中，模型只在3D模拟数据上进行训练，并将开箱即用的方式应用于各种真实的摄像机。我们提出了一种新的方法，通过增加仿真训练数据来学习稳健的表示，使得表示可以更好地推广到看不见的真实世界测试数据。其关键思想是将最硬的相机视图的特征与原始视图的对抗性特征混合在一起。我们将我们的方法称为SimAug。我们表明，SimAug在使用零实际训练数据的三个真实世界基准上取得了令人满意的结果，并且当使用领域内训练数据时，在斯坦福无人机和Virat/ActEV数据集上的性能达到了最先进的水平。代码和模型在https://next.cs.cmu.edu/simaug上发布。

This paper studies the problem of predicting future trajectories of people in unseen cameras of novel scenarios and views. We approach this problem through the real-data-free setting in which the model is trained only on 3D simulation data and applied out-of-the-box to a wide variety of real cameras. We propose a novel approach to learn robust representation through augmenting the simulation training data such that the representation can better generalize to unseen real-world test data. The key idea is to mix the feature of the hardest camera view with the adversarial feature of the original view. We refer to our method asSimAug. We show thatSimAugachieves promising results on three real-world benchmarks using zero real training data, and state-of-the-art performance in the Stanford Drone and the VIRAT/ActEV dataset when using in-domain training data. Code and models are released at https://next.cs.cmu.edu/simaug .

SimAug: Learning Robust Representations from Simulation for Trajectory Prediction

文献摘要

相似文献