Solving the Weather4cast Challenge via Visual Transformers for 3D Images
Not on the map. Why?
Abstract (arXiv)
Accurately forecasting the weather is an important task, as many real-world processes and decisions depend on future meteorological conditions. The NeurIPS 2022 challenge entitled Weather4cast poses the problem of predicting rainfall events for the next eight hours given the preceding hour of satellite observations as a context. Motivated by the recent success of transformer-based architectures in computer vision, we implement and propose two methodologies based on this architecture to tackle this challenge. We find that ensembling different transformers with some baseline models achieves the best performance we could measure on the unseen test data. Our approach has been ranked 3rd in the competition.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 17 of its 24 references that are in the map. First posted on arXiv 5 Dec 2022.
Builds on
17 of 24 references.
References · 17
- 2017Attention Is All You Needcited by 60,361
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
- 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
- 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
- 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,292
- 2021ViViT: A Video Vision Transformercited by 1,620
- 2018Attention U-Net: Learning Where to Look for the Pancreascited by 1,435
- 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,198
- 2021UNETR: Transformers for 3D Medical Image Segmentationcited by 959
- 2022Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Imagescited by 830
- 2017Focal Loss for Dense Object Detectioncited by 752
5 more
- 2015Empirical Evaluation of Rectified Activations in Convolutional Networkcited by 519
- 2021Skillful Precipitation Nowcasting using Deep Generative Models of Radarcited by 311
- 2020AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed Gradientscited by 283
- 2019Machine Learning for Precipitation Nowcasting from Radar Imagescited by 56
- 2021Improvements to short-term weather prediction with recurrent-convolutional networkscited by 4
Built on by
Citing papers per year: 2025: 2.
2 papers.