# Does Your VFM Speak Plant? The Botanical Grammar of Vision Foundation Models for Object Detection

arXiv: https://arxiv.org/abs/2604.09920 · HTML: https://mlsanity.com/paper/2604.09920/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 24 references that are in the map.
- First posted on arXiv 10 Apr 2026.

## Builds on (most cited first, 14 of 14)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [SAM 3: Segment Anything with Concepts](https://mlsanity.com/paper/2511.16719/) (2025)
- [YOLO-World: Real-Time Open-Vocabulary Object Detection](https://mlsanity.com/paper/2401.17270/) (2024)
- [Scaling Open-Vocabulary Object Detection](https://mlsanity.com/paper/2306.09683/) (2023)
- [Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery](https://mlsanity.com/paper/2302.03668/) (2023)
- [Prompting Hard or Hardly Prompting: Prompt Inversion for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2312.12416/) (2023)
- [Prompt Repetition Improves Non-Reasoning LLMs](https://mlsanity.com/paper/2512.14982/) (2025)
- [Open-Vocabulary Calibration for Fine-tuned CLIP](https://mlsanity.com/paper/2402.04655/) (2024)
- [Few-Shot Adaptation of Grounding DINO for Agricultural Domain](https://mlsanity.com/paper/2504.07252/) (2025)

## Built on by (most cited first, 1 of 1)

- [Text-conditioned Segmentation for Tomato Phenotyping via Procedural Synthetic Data](https://mlsanity.com/paper/2607.18576/) (2026)

## Abstract (arXiv)

Vision foundation models (VFMs) offer the promise of zero-shot object detection without task-specific training data, yet their performance in complex agricultural scenes remains highly sensitive to text prompt construction. We present a systematic prompt optimization framework evaluating four open-vocabulary detectors -- YOLO World, SAM3, Grounding DINO, and OWLv2 -- for cowpea flower and pod detection across synthetic and real field imagery. We decompose prompts into eight axes and conduct one-factor-at-a-time analysis followed by combinatorial optimization, revealing that models respond divergently to prompt structure: conditions that optimize one architecture can collapse another. Applying model-specific combinatorial prompts yields substantial gains over a naive species-name baseline, including +0.357 mAP@0.5 for YOLO World and +0.362 mAP@0.5 for OWLv2 on synthetic cowpea flower data. To evaluate cross-task generalization, we use an LLM to translate the discovered axis structure to a morphologically distinct target -- cowpea pods -- and compare against prompting using the discovered optimal structures from synthetic flower data. Crucially, prompt structures optimized exclusively on synthetic data transfer effectively to real-world fields: synthetic-pipeline prompts match or exceed those discovered on labeled real data for the majority of model-object combinations (flower: 0.374 vs. 0.353 for YOLO World; pod: 0.429 vs. 0.371 for SAM3). Our findings demonstrate that prompt engineering can substantially close the gap between zero-shot VFMs and supervised detectors without requiring manual annotation, and that optimal prompts are model-specific, non-obvious, and transferable across domains.