# Traffic4cast at NeurIPS 2021 -- Temporal and Spatial Few-Shot Transfer Learning in Gridded Geo-Spatial Processes

arXiv: https://arxiv.org/abs/2203.17070 · HTML: https://mlsanity.com/paper/2203.17070/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 73 references that are in the map.
- First posted on arXiv 31 Mar 2022.

## Builds on (most cited first, 30 of 36)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [UNet++: A Nested U-Net Architecture for Medical Image Segmentation](https://mlsanity.com/paper/1807.10165/) (2018)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation](https://mlsanity.com/paper/1912.05074/) (2019)
- [Unsupervised Learning of Video Representations using LSTMs](https://mlsanity.com/paper/1502.04681/) (2015)
- [Skillful Precipitation Nowcasting using Deep Generative Models of Radar](https://mlsanity.com/paper/2104.00954/) (2021)
- [Video Representation Learning by Dense Predictive Coding](https://mlsanity.com/paper/1909.04656/) (2019)
- [Stochastic Adversarial Video Prediction](https://mlsanity.com/paper/1804.01523/) (2018)
- [A review of domain adaptation without target labels](https://mlsanity.com/paper/1901.05335/) (2019)
- [MetNet: A Neural Weather Model for Precipitation Forecasting](https://mlsanity.com/paper/2003.12140/) (2020)
- [ETA Prediction with Graph Neural Networks in Google Maps](https://mlsanity.com/paper/2108.11482/) (2021)
- [A Review on Deep Learning Techniques for Video Prediction](https://mlsanity.com/paper/2004.05214/) (2020)
- [An introduction to domain adaptation and transfer learning](https://mlsanity.com/paper/1812.11806/) (2018)
- [An Uncertain Future: Forecasting from Static Images using Variational Autoencoders](https://mlsanity.com/paper/1606.07873/) (2016)
- [Machine Learning for Precipitation Nowcasting from Radar Images](https://mlsanity.com/paper/1912.12132/) (2019)
- [Visual Dynamics: Probabilistic Future Frame Synthesis via Cross Convolutional Networks](https://mlsanity.com/paper/1607.02586/) (2016)
- [Spatially-sparse convolutional neural networks](https://mlsanity.com/paper/1409.6070/) (2014)
- [Skillful Twelve Hour Precipitation Forecasts using Large Context Neural Networks](https://mlsanity.com/paper/2111.07470/) (2021)
- [CrevNet: Conditionally Reversible Video Prediction](https://mlsanity.com/paper/1910.11577/) (2019)
- [Utilizing UNet for the future traffic map prediction task Traffic4cast challenge 2020](https://mlsanity.com/paper/2012.00125/) (2020)
- [A Broader Study of Cross-Domain Few-Shot Learning](https://mlsanity.com/paper/1912.07200/) (2019)
- [Traffic4cast-Traffic Map Movie Forecasting -- Team MIE-Lab](https://mlsanity.com/paper/1910.13824/) (2019)
- [Traffic map prediction using UNet based deep convolutional neural network](https://mlsanity.com/paper/1912.05288/) (2019)
- [Learning to Transfer for Traffic Forecasting via Multi-task Learning](https://mlsanity.com/paper/2111.15542/) (2021)
- [Traffic4cast 2020 -- Graph Ensemble Net and the Importance of Feature And Loss Function Design for Traffic Prediction](https://mlsanity.com/paper/2012.02115/) (2020)
- [Semi-Supervised Learning for Cancer Detection of Lymph Node Metastases](https://mlsanity.com/paper/1906.09587/) (2019)
- [TLab: Traffic Map Movie Forecasting Based on HR-NET](https://mlsanity.com/paper/2011.07728/) (2020)
- [A Graph-based U-Net Model for Predicting Traffic in unseen Cities](https://mlsanity.com/paper/2202.06725/) (2022)

## Built on by (most cited first, 15 of 15)

- [Physics-Informed Graph Neural Networks for Water Distribution Systems](https://mlsanity.com/paper/2403.18570/) (2024)
- [PredBench: Benchmarking Spatio-Temporal Prediction across Diverse Disciplines](https://mlsanity.com/paper/2407.08418/) (2024)
- [Transposed Variational Auto-encoder with Intrinsic Feature Learning for Traffic Forecasting](https://mlsanity.com/paper/2211.00641/) (2022)
- [Spatial Graph Convolution Neural Networks for Water Distribution Systems](https://mlsanity.com/paper/2211.09587/) (2022)
- [Traffic4cast at NeurIPS 2022 -- Predict Dynamics along Graph Edges from Sparse Node Data: Whole City Traffic and ETA from Stationary Vehicle Detectors](https://mlsanity.com/paper/2303.07758/) (2023)
- [UniSTD: Towards Unified Spatio-Temporal Learning across Diverse Disciplines](https://mlsanity.com/paper/2503.20748/) (2025)
- [Hierarchical Graph Structures for Congestion and ETA Prediction](https://mlsanity.com/paper/2211.11762/) (2022)
- [Metropolitan Segment Traffic Speeds from Massive Floating Car Data in 10 Cities](https://mlsanity.com/paper/2302.08761/) (2023)
- [Large scale traffic forecasting with gradient boosting, Traffic4cast 2022 challenge](https://mlsanity.com/paper/2211.00157/) (2022)
- [Multi-task Learning for Sparse Traffic Forecasting](https://mlsanity.com/paper/2211.09984/) (2022)
- [An Efficient Two-stage Gradient Boosting Framework for Short-term Traffic State Estimation](https://mlsanity.com/paper/2302.10400/) (2023)
- [Uncertainty Quantification for Image-based Traffic Prediction across Cities](https://mlsanity.com/paper/2308.06129/) (2023)
- [Academic competitions](https://mlsanity.com/paper/2312.00268/) (2023)
- [Scalable and Robust Physics-Informed Graph Neural Networks for Water Distribution Systems](https://mlsanity.com/paper/2502.12164/) (2025)
- [A Road-Conditioned Traffic Movie Prediction Network with Spatiotemporal and Structure-Consistent Learning](https://mlsanity.com/paper/2605.27884/) (2026)

## Abstract (arXiv)

The IARAI Traffic4cast competitions at NeurIPS 2019 and 2020 showed that neural networks can successfully predict future traffic conditions 1 hour into the future on simply aggregated GPS probe data in time and space bins. We thus reinterpreted the challenge of forecasting traffic conditions as a movie completion task. U-Nets proved to be the winning architecture, demonstrating an ability to extract relevant features in this complex real-world geo-spatial process. Building on the previous competitions, Traffic4cast 2021 now focuses on the question of model robustness and generalizability across time and space. Moving from one city to an entirely different city, or moving from pre-COVID times to times after COVID hit the world thus introduces a clear domain shift. We thus, for the first time, release data featuring such domain shifts. The competition now covers ten cities over 2 years, providing data compiled from over 10^12 GPS probe data. Winning solutions captured traffic dynamics sufficiently well to even cope with these complex domain shifts. Surprisingly, this seemed to require only the previous 1h traffic dynamic history and static road graph as input.