SimVPv2: Towards Simple yet Powerful Spatiotemporal Predictive Learning
This work addresses the need for efficient and high-performing models in spatiotemporal predictive learning, such as for traffic forecasting and climate prediction, though it is incremental as it builds upon the SimVP baseline.
The paper tackles the complexity and computational overhead in spatiotemporal predictive learning by proposing SimVPv2, a streamlined model that uses plain convolutional layers with a Gated Spatiotemporal Attention mechanism, achieving state-of-the-art performance with fewer FLOPs, half the training time, and 60% faster inference on the Moving MNIST benchmark.
Recent years have witnessed remarkable advances in spatiotemporal predictive learning, with methods incorporating auxiliary inputs, complex neural architectures, and sophisticated training strategies. While SimVP has introduced a simpler, CNN-based baseline for this task, it still relies on heavy Unet-like architectures for spatial and temporal modeling, which still suffers from high complexity and computational overhead. In this paper, we propose SimVPv2, a streamlined model that eliminates the need for Unet architectures and demonstrates that plain stacks of convolutional layers, enhanced with an efficient Gated Spatiotemporal Attention mechanism, can deliver state-of-the-art performance. SimVPv2 not only simplifies the model architecture but also improves both performance and computational efficiency. On the standard Moving MNIST benchmark, SimVPv2 achieves superior performance compared to SimVP, with fewer FLOPs, about half the training time, and 60% faster inference efficiency. Extensive experiments across eight diverse datasets, including real-world tasks such as traffic forecasting and climate prediction, further demonstrate that SimVPv2 offers a powerful yet straightforward solution, achieving robust generalization across various spatiotemporal learning scenarios. We believe the proposed SimVPv2 can serve as a solid baseline to benefit the spatiotemporal predictive learning community.