ChatGPT and general-purpose AI count fruits in pictures surprisingly well without programming or training

General-purpose artificial intelligence (AI) can facilitate agricultural digitalization as many tools do not require coding. Yet, it remains unclear how well the emerging general-purpose AI technologies can perform object counting, which is a fundamental task in agricultural digitalization, in compa...

Full description

Saved in:
Bibliographic Details
Main Authors: Konlavach Mengsuwan, Juan C. Rivera-Palacio, Masahiro Ryo
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Smart Agricultural Technology
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2772375524002934
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850061352900493312
author Konlavach Mengsuwan
Juan C. Rivera-Palacio
Masahiro Ryo
author_facet Konlavach Mengsuwan
Juan C. Rivera-Palacio
Masahiro Ryo
author_sort Konlavach Mengsuwan
collection DOAJ
description General-purpose artificial intelligence (AI) can facilitate agricultural digitalization as many tools do not require coding. Yet, it remains unclear how well the emerging general-purpose AI technologies can perform object counting, which is a fundamental task in agricultural digitalization, in comparison to the current standard practice. We show that ChatGPT (GPT4 V) demonstrated moderate performance in counting coffee cherries from images, while the T-Rex, foundation model for object counting, performed with high accuracy. Testing with a hundred images, we examined that ChatGPT can count cherries, and the performance improves with human feedback (R2 = 0.36 and 0.46, respectively). The T-Rex foundation model required only a few samples for training but outperformed YOLOv8, the conventional best practice model (R2 = 0.92 and 0.90, respectively). Obtaining the results with these models was 100x shorter than the conventional best practice. These results bring two surprises for deep learning users in applied domains: a foundation model can drastically save effort and achieve higher accuracy than a conventional approach, and ChatGPT can reveal a relatively good performance especially with guidance by providing some examples and feedback. No requirement for coding skills can impact education, outreach, and real-world implementation of generative AI for supporting farmers.
format Article
id doaj-art-783ec4ea54e44d2ba71b01bd0f2ea2c5
institution DOAJ
issn 2772-3755
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Smart Agricultural Technology
spelling doaj-art-783ec4ea54e44d2ba71b01bd0f2ea2c52025-08-20T02:50:16ZengElsevierSmart Agricultural Technology2772-37552024-12-01910068810.1016/j.atech.2024.100688ChatGPT and general-purpose AI count fruits in pictures surprisingly well without programming or trainingKonlavach Mengsuwan0Juan C. Rivera-Palacio1Masahiro Ryo2Research Platform Data Analysis & Simulation, Leibniz Centre for Agricultural Landscape Research (ZALF), Müncheberg, Germany; Environment and Natural Sciences, Brandenburg University of Technology Cottbus‐Senftenberg, Cottbus, GermanyResearch Platform Data Analysis & Simulation, Leibniz Centre for Agricultural Landscape Research (ZALF), Müncheberg, Germany; Environment and Natural Sciences, Brandenburg University of Technology Cottbus‐Senftenberg, Cottbus, Germany; Alliance of Bioversity International and CIAT, Rome, ItalyResearch Platform Data Analysis & Simulation, Leibniz Centre for Agricultural Landscape Research (ZALF), Müncheberg, Germany; Environment and Natural Sciences, Brandenburg University of Technology Cottbus‐Senftenberg, Cottbus, Germany; Corresponding author at: Research Platform Data Analysis & Simulation, Leibniz Centre for Agricultural Landscape Research (ZALF), Müncheberg, Germany.General-purpose artificial intelligence (AI) can facilitate agricultural digitalization as many tools do not require coding. Yet, it remains unclear how well the emerging general-purpose AI technologies can perform object counting, which is a fundamental task in agricultural digitalization, in comparison to the current standard practice. We show that ChatGPT (GPT4 V) demonstrated moderate performance in counting coffee cherries from images, while the T-Rex, foundation model for object counting, performed with high accuracy. Testing with a hundred images, we examined that ChatGPT can count cherries, and the performance improves with human feedback (R2 = 0.36 and 0.46, respectively). The T-Rex foundation model required only a few samples for training but outperformed YOLOv8, the conventional best practice model (R2 = 0.92 and 0.90, respectively). Obtaining the results with these models was 100x shorter than the conventional best practice. These results bring two surprises for deep learning users in applied domains: a foundation model can drastically save effort and achieve higher accuracy than a conventional approach, and ChatGPT can reveal a relatively good performance especially with guidance by providing some examples and feedback. No requirement for coding skills can impact education, outreach, and real-world implementation of generative AI for supporting farmers.http://www.sciencedirect.com/science/article/pii/S2772375524002934Foundation modelGeneral purpose aiChatgptLarge language modelLarge vision language modelagriculture
spellingShingle Konlavach Mengsuwan
Juan C. Rivera-Palacio
Masahiro Ryo
ChatGPT and general-purpose AI count fruits in pictures surprisingly well without programming or training
Smart Agricultural Technology
Foundation model
General purpose ai
Chatgpt
Large language model
Large vision language model
agriculture
title ChatGPT and general-purpose AI count fruits in pictures surprisingly well without programming or training
title_full ChatGPT and general-purpose AI count fruits in pictures surprisingly well without programming or training
title_fullStr ChatGPT and general-purpose AI count fruits in pictures surprisingly well without programming or training
title_full_unstemmed ChatGPT and general-purpose AI count fruits in pictures surprisingly well without programming or training
title_short ChatGPT and general-purpose AI count fruits in pictures surprisingly well without programming or training
title_sort chatgpt and general purpose ai count fruits in pictures surprisingly well without programming or training
topic Foundation model
General purpose ai
Chatgpt
Large language model
Large vision language model
agriculture
url http://www.sciencedirect.com/science/article/pii/S2772375524002934
work_keys_str_mv AT konlavachmengsuwan chatgptandgeneralpurposeaicountfruitsinpicturessurprisinglywellwithoutprogrammingortraining
AT juancriverapalacio chatgptandgeneralpurposeaicountfruitsinpicturessurprisinglywellwithoutprogrammingortraining
AT masahiroryo chatgptandgeneralpurposeaicountfruitsinpicturessurprisinglywellwithoutprogrammingortraining