Salvato in:
Dettagli Bibliografici
Autori principali: Islam, Ashhadul, Biswas, Md. Rafiul, Zaghouani, Wajdi, Belhaouari, Samir Brahim, Shah, Zubair
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:https://arxiv.org/abs/2401.00127
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910284789055488
author Islam, Ashhadul
Biswas, Md. Rafiul
Zaghouani, Wajdi
Belhaouari, Samir Brahim
Shah, Zubair
author_facet Islam, Ashhadul
Biswas, Md. Rafiul
Zaghouani, Wajdi
Belhaouari, Samir Brahim
Shah, Zubair
contents $ $The synergy of language and vision models has given rise to Large Language and Vision Assistant models (LLVAs), designed to engage users in rich conversational experiences intertwined with image-based queries. These comprehensive multimodal models seamlessly integrate vision encoders with Large Language Models (LLMs), expanding their applications in general-purpose language and visual comprehension. The advent of Large Multimodal Models (LMMs) heralds a new era in Artificial Intelligence (AI) assistance, extending the horizons of AI utilization. This paper takes a unique perspective on LMMs, exploring their efficacy in performing image classification tasks using tailored prompts designed for specific datasets. We also investigate the LLVAs zero-shot learning capabilities. Our study includes a benchmarking analysis across four diverse datasets: MNIST, Cats Vs. Dogs, Hymnoptera (Ants Vs. Bees), and an unconventional dataset comprising Pox Vs. Non-Pox skin images. The results of our experiments demonstrate the model's remarkable performance, achieving classification accuracies of 85\%, 100\%, 77\%, and 79\% for the respective datasets without any fine-tuning. To bolster our analysis, we assess the model's performance post fine-tuning for specific tasks. In one instance, fine-tuning is conducted over a dataset comprising images of faces of children with and without autism. Prior to fine-tuning, the model demonstrated a test accuracy of 55\%, which significantly improved to 83\% post fine-tuning. These results, coupled with our prior findings, underscore the transformative potential of LLVAs and their versatile applications in real-world scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2401_00127
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Pushing Boundaries: Exploring Zero Shot Object Classification with Large Multimodal Models
Islam, Ashhadul
Biswas, Md. Rafiul
Zaghouani, Wajdi
Belhaouari, Samir Brahim
Shah, Zubair
Computer Vision and Pattern Recognition
Social and Information Networks
$ $The synergy of language and vision models has given rise to Large Language and Vision Assistant models (LLVAs), designed to engage users in rich conversational experiences intertwined with image-based queries. These comprehensive multimodal models seamlessly integrate vision encoders with Large Language Models (LLMs), expanding their applications in general-purpose language and visual comprehension. The advent of Large Multimodal Models (LMMs) heralds a new era in Artificial Intelligence (AI) assistance, extending the horizons of AI utilization. This paper takes a unique perspective on LMMs, exploring their efficacy in performing image classification tasks using tailored prompts designed for specific datasets. We also investigate the LLVAs zero-shot learning capabilities. Our study includes a benchmarking analysis across four diverse datasets: MNIST, Cats Vs. Dogs, Hymnoptera (Ants Vs. Bees), and an unconventional dataset comprising Pox Vs. Non-Pox skin images. The results of our experiments demonstrate the model's remarkable performance, achieving classification accuracies of 85\%, 100\%, 77\%, and 79\% for the respective datasets without any fine-tuning. To bolster our analysis, we assess the model's performance post fine-tuning for specific tasks. In one instance, fine-tuning is conducted over a dataset comprising images of faces of children with and without autism. Prior to fine-tuning, the model demonstrated a test accuracy of 55\%, which significantly improved to 83\% post fine-tuning. These results, coupled with our prior findings, underscore the transformative potential of LLVAs and their versatile applications in real-world scenarios.
title Pushing Boundaries: Exploring Zero Shot Object Classification with Large Multimodal Models
topic Computer Vision and Pattern Recognition
Social and Information Networks
url https://arxiv.org/abs/2401.00127