Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.16179 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909047660216320 |
|---|---|
| author | Tiwary, Piyush Ahuja, Utkarsh Sani, Depanshu Jayagopal, Aishwarya Gubbi, Sagar Venugopalan, Subhashini Talekar, Alok Rajan, Vaibhav |
| author_facet | Tiwary, Piyush Ahuja, Utkarsh Sani, Depanshu Jayagopal, Aishwarya Gubbi, Sagar Venugopalan, Subhashini Talekar, Alok Rajan, Vaibhav |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_16179 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MAgSeg: Segmentation of Agricultural Landscapes in High-Resolution Satellite Imagery using Multimodal Large Language Models Tiwary, Piyush Ahuja, Utkarsh Sani, Depanshu Jayagopal, Aishwarya Gubbi, Sagar Venugopalan, Subhashini Talekar, Alok Rajan, Vaibhav Computer Vision and Pattern Recognition 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. |
| title | MAgSeg: Segmentation of Agricultural Landscapes in High-Resolution Satellite Imagery using Multimodal Large Language Models |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.16179 |