# Vision-Language Semantic Grounding for Multi-Domain Crop-Weed Segmentation

arXiv: https://arxiv.org/abs/2602.23677 · HTML: https://mlsanity.com/paper/2602.23677/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 28 references that are in the map.
- First posted on arXiv 27 Feb 2026.

## Builds on (most cited first, 11 of 11)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Contrastive Learning of Medical Visual Representations from Paired Images and Text](https://mlsanity.com/paper/2010.00747/) (2020)
- [Characterizing and Avoiding Negative Transfer](https://mlsanity.com/paper/1811.09751/) (2018)
- [MSeg: A Composite Dataset for Multi-domain Semantic Segmentation](https://mlsanity.com/paper/2112.13762/) (2021)
- [Leveraging Vision Language Models for Specialized Agricultural Tasks](https://mlsanity.com/paper/2407.19617/) (2024)
- [AgroGPT: Efficient Agricultural Vision-Language Model with Expert Tuning](https://mlsanity.com/paper/2410.08405/) (2024)
- [Vision Transformer Adapters for Generalizable Multitask Learning](https://mlsanity.com/paper/2308.12372/) (2023)
- [Improved Crop and Weed Detection with Diverse Data Ensemble Learning](https://mlsanity.com/paper/2310.01055/) (2023)

## Built on by (most cited first, 2 of 2)

- [Super-Generalist: Towards Comprehensive and Accurate Medical Image Understanding via Generalist-Specialist Synergy](https://mlsanity.com/paper/2607.09135/) (2026)
- [Think with Extra-Image: A Farmland Segmentation Agent Driven by Spatio-Temporal Information Gain](https://mlsanity.com/paper/2607.28186/) (2026)

## Abstract (arXiv)

Fine-grained crop-weed segmentation is essential for enabling targeted herbicide application in precision agriculture. However, existing deep learning models struggle to generalize across heterogeneous agricultural environments due to reliance on dataset-specific visual features. We propose Vision-Language Weed Segmentation (VL-WS), a novel framework that addresses this limitation by grounding pixel-level segmentation in semantically aligned, domain-invariant representations. Our architecture employs a dual-encoder design, where frozen Contrastive Language-Image Pretraining (CLIP) embeddings and task-specific spatial features are fused and modulated via Feature-wise Linear Modulation (FiLM) layers conditioned on natural language captions. This design enables image level textual descriptions to guide channel-wise feature refinement while preserving fine-grained spatial localization. Unlike prior works restricted to training and evaluation on single-source datasets, VL-WS is trained on a unified corpus that includes close-range ground imagery (robotic platforms) and high-altitude UAV imagery, covering diverse crop types, weed species, growth stages, and sensing conditions. Experimental results across four benchmark datasets demonstrate the effectiveness of our framework, with VL-WS achieving a mean Dice score of 91.64% and outperforming the CNN baseline by 4.98%. The largest gains occur on the most challenging weed class, where VL-WS attains 80.45% Dice score compared to 65.03% for the best baseline, representing a 15.42% improvement. VL-WS further maintains stable weed segmentation performance under limited target-domain supervision, indicating improved generalization and data efficiency. These findings highlight the potential of vision-language alignment to enable scalable, label-efficient segmentation models deployable across diverse real-world agricultural domains.