SimVPv2: Towards Simple yet Powerful Spatiotemporal Predictive Learning

• URL: http://arxiv.org/abs/2211.12509v4
• Date: Thu, 12 Dec 2024 08:54:14 GMT
• Title: SimVPv2: Towards Simple yet Powerful Spatiotemporal Predictive Learning
• Authors: Cheng Tan, Zhangyang Gao, Siyuan Li, Stan Z. Li,
• Abstract summary: We propose SimVPv2, a streamlined model that eliminates the need for Unet architectures for spatial and temporal modeling. 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.
• Score: 61.419914155985886
• License:
• Abstract: 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.

Related papers

• Tao: Re-Thinking DL-based Microarchitecture Simulation [8.501776613988484]
  Existing microarchitecture simulators excel and fall short at different aspects. Deep learning (DL)-based simulations are remarkably fast and have acceptable accuracy but fail to provide adequate low-level microarchitectural performance metrics. This paper introduces TAO that redesigns the DL-based simulation with three primary contributions.
  arXiv  Detail & Related papers  (2024-04-16T21:45:10Z)
• Bridging the Sim-to-Real Gap with Bayesian Inference [53.61496586090384]
  We present SIM-FSVGD for learning robot dynamics from data. We use low-fidelity physical priors to regularize the training of neural network models. We demonstrate the effectiveness of SIM-FSVGD in bridging the sim-to-real gap on a high-performance RC racecar system.
  arXiv  Detail & Related papers  (2024-03-25T11:29:32Z)
• Predicting Traffic Flow with Federated Learning and Graph Neural with Asynchronous Computations Network [0.0]
  We present a novel deep-learning method called Federated Learning and Asynchronous Graph Convolutional Networks (FLAGCN) Our framework incorporates the principles of asynchronous graph convolutional networks with federated learning to enhance accuracy and efficiency of real-time traffic flow prediction.
  arXiv  Detail & Related papers  (2024-01-05T09:36:42Z)
• Representation Learning with Multi-Step Inverse Kinematics: An Efficient and Optimal Approach to Rich-Observation RL [106.82295532402335]
  Existing reinforcement learning algorithms suffer from computational intractability, strong statistical assumptions, and suboptimal sample complexity. We provide the first computationally efficient algorithm that attains rate-optimal sample complexity with respect to the desired accuracy level. Our algorithm, MusIK, combines systematic exploration with representation learning based on multi-step inverse kinematics.
  arXiv  Detail & Related papers  (2023-04-12T14:51:47Z)
• On Fast Simulation of Dynamical System with Neural Vector Enhanced Numerical Solver [59.13397937903832]
  We introduce a deep learning-based corrector called Neural Vector (NeurVec) NeurVec can compensate for integration errors and enable larger time step sizes in simulations. Our experiments on a variety of complex dynamical system benchmarks demonstrate that NeurVec exhibits remarkable generalization capability.
  arXiv  Detail & Related papers  (2022-08-07T09:02:18Z)
• Improving Sample Efficiency of Value Based Models Using Attention and Vision Transformers [52.30336730712544]
  We introduce a deep reinforcement learning architecture whose purpose is to increase sample efficiency without sacrificing performance. We propose a visually attentive model that uses transformers to learn a self-attention mechanism on the feature maps of the state representation. We demonstrate empirically that this architecture improves sample complexity for several Atari environments, while also achieving better performance in some of the games.
  arXiv  Detail & Related papers  (2022-02-01T19:03:03Z)
• Deep Bayesian Active Learning for Accelerating Stochastic Simulation [74.58219903138301]
  Interactive Neural Process (INP) is a deep active learning framework for simulations and with active learning approaches. For active learning, we propose a novel acquisition function, Latent Information Gain (LIG), calculated in the latent space of NP based models. The results demonstrate STNP outperforms the baselines in the learning setting and LIG achieves the state-of-the-art for active learning.
  arXiv  Detail & Related papers  (2021-06-05T01:31:51Z)
• Multi-objective Neural Architecture Search with Almost No Training [9.93048700248444]
  We propose an effective alternative, dubbed Random-Weight Evaluation (RWE), to rapidly estimate the performance of network architectures. RWE reduces the computational cost of evaluating an architecture from hours to seconds. When integrated within an evolutionary multi-objective algorithm, RWE obtains a set of efficient architectures with state-of-the-art performance on CIFAR-10 with less than two hours' searching on a single GPU card.
  arXiv  Detail & Related papers  (2020-11-27T07:39:17Z)
• Federated Transfer Learning with Dynamic Gradient Aggregation [27.42998421786922]
  This paper introduces a Federated Learning (FL) simulation platform for Acoustic Model training. The proposed FL platform can support different tasks based on the adopted modular design. It is shown to outperform the golden standard of distributed training in both convergence speed and overall model performance.
  arXiv  Detail & Related papers  (2020-08-06T04:29:01Z)
• STONNE: A Detailed Architectural Simulator for Flexible Neural Network Accelerators [5.326345912766044]
  STONNE is a cycle-accurate, highly-modular and highly-extensible simulation framework. We show how it can closely approach the performance results of the publicly available BSV-coded MAERI implementation.
  arXiv  Detail & Related papers  (2020-06-10T19:20:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.