# A Comparative Study of Transformer and Convolutional Models for Crop Segmentation from Satellite Image Time Series

arXiv: https://arxiv.org/abs/2412.01944 · HTML: https://mlsanity.com/paper/2412.01944/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 28 references that are in the map.
- First posted on arXiv 2 Dec 2024.

## Builds on (most cited first, 10 of 10)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers](https://mlsanity.com/paper/2012.15840/) (2020)
- [Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Images](https://mlsanity.com/paper/2201.01266/) (2022)
- [SpectralFormer: Rethinking Hyperspectral Image Classification with Transformers](https://mlsanity.com/paper/2107.02988/) (2021)
- [UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene Imagery](https://mlsanity.com/paper/2109.08937/) (2021)
- [Multi-Temporal Land Cover Classification with Sequential Recurrent Encoders](https://mlsanity.com/paper/1802.02080/) (2018)
- [ViTs for SITS: Vision Transformers for Satellite Image Time Series](https://mlsanity.com/paper/2301.04944/) (2023)

## Abstract (arXiv)

Crop segmentation from satellite image time series (SITS) is a fundamental task for agricultural monitoring and land-use analysis. While convolutional neural networks (CNNs) have been widely used, transformer-based architectures offer alternative mechanisms for representing spatial and temporal dependencies in multispectral data. This paper presents a comparative study of CNN and transformer-based segmentation models for crop mapping from Sentinel-2 time series, including 3D U-Net, 3D FPN, 3D DeepLabv3, and three transformer architectures: Swin UNETR, TSViT, and VistaFormer, which adopt different strategies for capturing temporal dependencies. Experiments on the Munich and Lombardia datasets show that TSViT achieves the best overall results, slightly surpassing 3D U-Net, which remains a strong CNN baseline. VistaFormer offers the best efficiency, while Swin UNETR performs competitively but is less effective than transformers that explicitly model temporal dynamics. These results highlight that temporal modelling is critical for SITS: TSViT outperforms CNNs and approaches that treat time as an additional spatial dimension, while VistaFormer provides a strong efficiency-performance trade-off.