计算机科学
水准点(测量)
机器学习
人工智能
基线(sea)
一般化
简单(哲学)
卷积神经网络
还原(数学)
深度学习
数学
数学分析
哲学
海洋学
几何学
大地测量学
认识论
地理
地质学
作者
Cheng Tan,Zhangyang Gao,Siyuan Li,Stan Z. Li
出处
期刊:Cornell University - arXiv
日期:2022-01-01
被引量:19
标识
DOI:10.48550/arxiv.2211.12509
摘要
Recent years have witnessed remarkable advances in spatiotemporal predictive learning, incorporating auxiliary inputs, elaborate neural architectures, and sophisticated training strategies. Although impressive, the system complexity of mainstream methods is increasing as well, which may hinder the convenient applications. This paper proposes SimVP, a simple spatiotemporal predictive baseline model that is completely built upon convolutional networks without recurrent architectures and trained by common mean squared error loss in an end-to-end fashion. Without introducing any extra tricks and strategies, SimVP can achieve superior performance on various benchmark datasets. To further improve the performance, we derive variants with the gated spatiotemporal attention translator from SimVP that can achieve better performance. We demonstrate that SimVP has strong generalization and extensibility on real-world datasets through extensive experiments. The significant reduction in training cost makes it easier to scale to complex scenarios. We believe SimVP can serve as a solid baseline to benefit the spatiotemporal predictive learning community.
科研通智能强力驱动
Strongly Powered by AbleSci AI