---
title: "MAgSeg: Segmentation of Agricultural Landscapes in High-Resolution Satellite Imagery using Multimodal Large Language Models"
authors:
  - "Piyush Tiwary"
  - "Utkarsh Ahuja"
  - "Depanshu Sani"
  - "Aishwarya Jayagopal"
  - "Sagar Gubbi"
  - "Subhashini Venugopalan"
  - "Alok Talekar"
  - "Vaibhav Rajan"
doi: "10.24963/ijcai.2026/728"
url: "https://ijcai.org/proceedings/2026/728"
pdf: "https://ijcai.org/proceedings/2026/0728.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "6546-6554"
track: "AI4Tech: AI Enabling Technologies"
keywords:
  - "Domain-specific AI4Tech: AI4Agriculture"
---

# MAgSeg: Segmentation of Agricultural Landscapes in High-Resolution Satellite Imagery using Multimodal Large Language Models

Piyush Tiwary, Utkarsh Ahuja, Depanshu Sani, Aishwarya Jayagopal, Sagar Gubbi, Subhashini Venugopalan, Alok Talekar, Vaibhav Rajan

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 6546-6554. DOI: [10.24963/ijcai.2026/728](https://doi.org/10.24963/ijcai.2026/728)

## Abstract

Agricultural landscape segmentation in the Global South is challenging as it is characterized by fragmented plots, high intra-class variance, and a scarcity of labeled training data. Recent advances in segmentation have been made by Multimodal Large Language Models (MLLMs). However, current approaches encounter critical context length bottlenecks and a domain alignment gap in understanding satellite features. We address these limitations through MAgSeg, a novel, decoder-free MLLM segmentation approach. MAgSeg is an architecturally efficient approach that enables standard MLLMs to perform segmentation of complex smallholder agricultural landscapes from high-resolution satellite imagery, without requiring auxiliary vision decoders. We introduce a novel instruction tuning data format designed to enable scalable fine-tuning and post-training on high resolution satellite imagery, which enables MAgSeg to learn from the global context of the image while generating text tokens for only a patch within the image. Extensive evaluations on datasets spanning three countries in the Global South demonstrate that MAgSeg significantly outperforms state-of-the-art MLLM baselines, offering a scalable solution to map smallholder agricultural environments.