# VistaFormer: Scalable Vision Transformers for Satellite Image Time Series Segmentation

Source: [VistaFormer: Scalable Vision Transformers for Satellite Image Time Series Segmentation](<https://www.sota2.com/research/paper/68fa74cf1e209131cea64081>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T03:19:27.756Z

Authors: Ezra MacDonald, Derek Jacoby, Yvonne Coady

Published: 2024-09-13T01:19:53.000Z

## Abstract

We introduce VistaFormer, a lightweight Transformer-based model architecture for the semantic segmentation of remote-sensing images. This model uses a multi-scale Transformer-based encoder with a lightweight decoder that aggregates global and local attention captured in the encoder blocks. VistaFormer uses position-free self-attention layers which simplifies the model architecture and removes the need to interpolate temporal and spatial codes, which can reduce model performance when training and testing image resolutions differ. We investigate simple techniques for filtering noisy input signals like clouds and demonstrate that improved model scalability can be achieved by substituting Multi-Head Self-Attention (MHSA) with Neighbourhood Attention (NA). Experiments on the PASTIS and MTLCC crop-type segmentation benchmarks show that VistaFormer achieves better performance than comparable models and requires only 8% of the floating point operations using MHSA and 11% using NA while also using fewer trainable parameters. VistaFormer with MHSA improves on state-of-the-art mIoU scores by 0.1% on the PASTIS benchmark and 3% on the MTLCC benchmark while VistaFormer with NA improves on the MTLCC benchmark by 3.7%.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2409.08461>)

[PDF](<https://arxiv.org/pdf/2409.08461.pdf>)
