Few-Shot Adaptation of Grounding DINO for Agricultural Domain
This work addresses the challenge of automating agricultural monitoring with minimal data, offering a practical solution for domain-specific applications, though it is incremental in adapting existing models.
The paper tackled the problem of limited annotated data in agricultural object detection by proposing a few-shot adaptation method for Grounding DINO, which achieved up to 24% higher mAP than fine-tuned YOLO models and outperformed previous state-of-the-art methods by 10% in remote sensing tasks.
Deep learning models are transforming agricultural applications by enabling automated phenotyping, monitoring, and yield estimation. However, their effectiveness heavily depends on large amounts of annotated training data, which can be labor and time intensive. Recent advances in open-set object detection, particularly with models like Grounding-DINO, offer a potential solution to detect regions of interests based on text prompt input. Initial zero-shot experiments revealed challenges in crafting effective text prompts, especially for complex objects like individual leaves and visually similar classes. To address these limitations, we propose an efficient few-shot adaptation method that simplifies the Grounding-DINO architecture by removing the text encoder module (BERT) and introducing a randomly initialized trainable text embedding. This method achieves superior performance across multiple agricultural datasets, including plant-weed detection, plant counting, insect identification, fruit counting, and remote sensing tasks. Specifically, it demonstrates up to a $\sim24\%$ higher mAP than fully fine-tuned YOLO models on agricultural datasets and outperforms previous state-of-the-art methods by $\sim10\%$ in remote sensing, under few-shot learning conditions. Our method offers a promising solution for automating annotation and accelerating the development of specialized agricultural AI solutions.