ChatGPT and general-purpose AI count fruits in pictures surprisingly well

TL;DR

This study shows that foundation models like T-Rex and ChatGPT can effectively count fruits in images with minimal training, saving time and effort compared to traditional deep learning models like YOLOv8.

Contribution

The paper demonstrates that foundation models and ChatGPT can perform object counting tasks with few-shot learning, reducing data requirements and implementation time in practical applications.

Findings

Foundation model with few-shot learning outperforms YOLOv8 in accuracy.

ChatGPT shows promising counting performance with minimal training.

Implementation time for foundation models and ChatGPT is significantly shorter.

Abstract

Object counting is a popular task in deep learning applications in various domains, including agriculture. A conventional deep learning approach requires a large amount of training data, often a logistic problem in a real-world application. To address this issue, we examined how well ChatGPT (GPT4V) and a general-purpose AI (foundation model for object counting, T-Rex) can count the number of fruit bodies (coffee cherries) in 100 images. The foundation model with few-shot learning outperformed the trained YOLOv8 model (R2 = 0.923 and 0.900, respectively). ChatGPT also showed some interesting potential, especially when few-shot learning with human feedback was applied (R2 = 0.360 and 0.460, respectively). Moreover, we examined the time required for implementation as a practical question. Obtaining the results with the foundation model and ChatGPT were much shorter than the YOLOv8 model (0.83 hrs, 1.75 hrs, and 161 hrs). We interpret these results as two surprises for deep learning users in applied domains: a foundation model with few-shot domain-specific learning can drastically save time and effort compared to the conventional approach, and ChatGPT can reveal a relatively good performance. Both approaches do not need coding skills, which can foster AI education and dissemination.