论文标题
希望：用于占用流量预测的分层时空网络
HOPE: Hierarchical Spatial-temporal Network for Occupancy Flow Prediction
论文作者
论文摘要
在本报告中，我们在CVPR 2022的Waymo Open数据集挑战中介绍了解决方案和流程预测挑战，该挑战在排行榜上排名第一。我们已经开发了一个新型的层次空间 - 临时网络，该网络具有时空编码器，一个富含潜在变量的多尺度聚合器以及一个递归分层的3D解码器。我们使用多种损失，包括局灶性损失和修改的流量痕量损失来有效指导训练过程。我们的方法达到了一个占地0.8389的流动占用AUC，并且优于排行榜上所有其他团队。
In this report, we introduce our solution to the Occupancy and Flow Prediction challenge in the Waymo Open Dataset Challenges at CVPR 2022, which ranks 1st on the leaderboard. We have developed a novel hierarchical spatial-temporal network featured with spatial-temporal encoders, a multi-scale aggregator enriched with latent variables, and a recursive hierarchical 3D decoder. We use multiple losses including focal loss and modified flow trace loss to efficiently guide the training process. Our method achieves a Flow-Grounded Occupancy AUC of 0.8389 and outperforms all the other teams on the leaderboard.
