UniSTD: Towards Unified Spatio-Temporal Learning across Diverse Disciplines

• URL: http://arxiv.org/abs/2503.20748v1
• Date: Wed, 26 Mar 2025 17:33:23 GMT
• Title: UniSTD: Towards Unified Spatio-Temporal Learning across Diverse Disciplines
• Authors: Chen Tang, Xinzhu Ma, Encheng Su, Xiufeng Song, Xiaohong Liu, Wei-Hong Li, Lei Bai, Wanli Ouyang, Xiangyu Yue,
• Abstract summary: We introduce bfUnistage, a unified Transformer-based framework fortemporal modeling.<n>Our work demonstrates that a task-specific vision-text can build a generalizable model fortemporal learning.<n>We also introduce a temporal module to incorporate temporal dynamics explicitly.
• Score: 64.84631333071728
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Traditional spatiotemporal models generally rely on task-specific architectures, which limit their generalizability and scalability across diverse tasks due to domain-specific design requirements. In this paper, we introduce \textbf{UniSTD}, a unified Transformer-based framework for spatiotemporal modeling, which is inspired by advances in recent foundation models with the two-stage pretraining-then-adaption paradigm. Specifically, our work demonstrates that task-agnostic pretraining on 2D vision and vision-text datasets can build a generalizable model foundation for spatiotemporal learning, followed by specialized joint training on spatiotemporal datasets to enhance task-specific adaptability. To improve the learning capabilities across domains, our framework employs a rank-adaptive mixture-of-expert adaptation by using fractional interpolation to relax the discrete variables so that can be optimized in the continuous space. Additionally, we introduce a temporal module to incorporate temporal dynamics explicitly. We evaluate our approach on a large-scale dataset covering 10 tasks across 4 disciplines, demonstrating that a unified spatiotemporal model can achieve scalable, cross-task learning and support up to 10 tasks simultaneously within one model while reducing training costs in multi-domain applications. Code will be available at https://github.com/1hunters/UniSTD.

Related papers

• Specialized Foundation Models Struggle to Beat Supervised Baselines [60.23386520331143]
  We look at three modalities -- genomics, satellite imaging, and time series -- with multiple recent FMs and compare them to a standard supervised learning workflow.<n>We find that it is consistently possible to train simple supervised models that match or even outperform the latest foundation models.
  arXiv  Detail & Related papers  (2024-11-05T04:10:59Z)
• Get Rid of Isolation: A Continuous Multi-task Spatio-Temporal Learning Framework [10.33844348594636]
  We argue that there is an essential to propose a Continuous Multi-task Spatiotemporal learning framework (CMuST) to empower collective urban intelligence.<n>CMuST reforms the urbantemporal learning from singledomain to cooperatively multi-task learning.<n>We establish a benchmark of three cities for multi-tasktemporal learning, and empirically demonstrate the superiority of CMuST.
  arXiv  Detail & Related papers  (2024-10-14T14:04:36Z)
• A Practitioner's Guide to Continual Multimodal Pretraining [83.63894495064855]
  Multimodal foundation models serve numerous applications at the intersection of vision and language.<n>To keep models updated, research into continual pretraining mainly explores scenarios with either infrequent, indiscriminate updates on large-scale new data, or frequent, sample-level updates.<n>We introduce FoMo-in-Flux, a continual multimodal pretraining benchmark with realistic compute constraints and practical deployment requirements.
  arXiv  Detail & Related papers  (2024-08-26T17:59:01Z)
• GPT-ST: Generative Pre-Training of Spatio-Temporal Graph Neural Networks [24.323017830938394]
  This work aims to address challenges by introducing a pre-training framework that seamlessly integrates with baselines and enhances their performance. The framework is built upon two key designs: (i) We propose a. apple-to-apple mask autoencoder as a pre-training model for learning-temporal dependencies. These modules are specifically designed to capture intra-temporal customized representations and semantic- and inter-cluster relationships.
  arXiv  Detail & Related papers  (2023-11-07T02:36:24Z)
• UniTime: A Language-Empowered Unified Model for Cross-Domain Time Series Forecasting [59.11817101030137]
  This research advocates for a unified model paradigm that transcends domain boundaries. Learning an effective cross-domain model presents the following challenges. We propose UniTime for effective cross-domain time series learning.
  arXiv  Detail & Related papers  (2023-10-15T06:30:22Z)
• TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting [24.834846119163885]
  We propose a novel framework, TEMPO, that can effectively learn time series representations. TEMPO expands the capability for dynamically modeling real-world temporal phenomena from data within diverse domains.
  arXiv  Detail & Related papers  (2023-10-08T00:02:25Z)
• TACTiS-2: Better, Faster, Simpler Attentional Copulas for Multivariate Time Series [57.4208255711412]
  Building on copula theory, we propose a simplified objective for the recently-introduced transformer-based attentional copulas (TACTiS) We show that the resulting model has significantly better training dynamics and achieves state-of-the-art performance across diverse real-world forecasting tasks.
  arXiv  Detail & Related papers  (2023-10-02T16:45:19Z)
• Effective Adaptation in Multi-Task Co-Training for Unified Autonomous Driving [103.745551954983]
  In this paper, we investigate the transfer performance of various types of self-supervised methods, including MoCo and SimCLR, on three downstream tasks. We find that their performances are sub-optimal or even lag far behind the single-task baseline. We propose a simple yet effective pretrain-adapt-finetune paradigm for general multi-task training.
  arXiv  Detail & Related papers  (2022-09-19T12:15:31Z)
• Learning Behavior Representations Through Multi-Timescale Bootstrapping [8.543808476554695]
  We introduce Bootstrap Across Multiple Scales (BAMS), a multi-scale representation learning model for behavior. We first apply our method on a dataset of quadrupeds navigating in different terrain types, and show that our model captures the temporal complexity of behavior.
  arXiv  Detail & Related papers  (2022-06-14T17:57:55Z)

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.