Saved in:
Bibliographic Details
Main Authors: Wu, Wenhao, Yao, Huanjin, Zhang, Mengxi, Song, Yuxin, Ouyang, Wanli, Wang, Jingdong
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2311.15732
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910363757314048
author Wu, Wenhao
Yao, Huanjin
Zhang, Mengxi
Song, Yuxin
Ouyang, Wanli
Wang, Jingdong
author_facet Wu, Wenhao
Yao, Huanjin
Zhang, Mengxi
Song, Yuxin
Ouyang, Wanli
Wang, Jingdong
contents This paper does not present a novel method. Instead, it delves into an essential, yet must-know baseline in light of the latest advancements in Generative Artificial Intelligence (GenAI): the utilization of GPT-4 for visual understanding. Our study centers on the evaluation of GPT-4's linguistic and visual capabilities in zero-shot visual recognition tasks: Firstly, we explore the potential of its generated rich textual descriptions across various categories to enhance recognition performance without any training. Secondly, we evaluate GPT-4's visual proficiency in directly recognizing diverse visual content. We conducted extensive experiments to systematically evaluate GPT-4's performance across images, videos, and point clouds, using 16 benchmark datasets to measure top-1 and top-5 accuracy. Our findings show that GPT-4, enhanced with rich linguistic descriptions, significantly improves zero-shot recognition, offering an average top-1 accuracy increase of 7% across all datasets. GPT-4 excels in visual recognition, outshining OpenAI-CLIP's ViT-L and rivaling EVA-CLIP's ViT-E, particularly in video datasets HMDB-51 and UCF-101, where it leads by 22% and 9%, respectively. We hope this research contributes valuable data points and experience for future studies. We release our code at https://github.com/whwu95/GPT4Vis.
format Preprint
id arxiv_https___arxiv_org_abs_2311_15732
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle GPT4Vis: What Can GPT-4 Do for Zero-shot Visual Recognition?
Wu, Wenhao
Yao, Huanjin
Zhang, Mengxi
Song, Yuxin
Ouyang, Wanli
Wang, Jingdong
Computer Vision and Pattern Recognition
This paper does not present a novel method. Instead, it delves into an essential, yet must-know baseline in light of the latest advancements in Generative Artificial Intelligence (GenAI): the utilization of GPT-4 for visual understanding. Our study centers on the evaluation of GPT-4's linguistic and visual capabilities in zero-shot visual recognition tasks: Firstly, we explore the potential of its generated rich textual descriptions across various categories to enhance recognition performance without any training. Secondly, we evaluate GPT-4's visual proficiency in directly recognizing diverse visual content. We conducted extensive experiments to systematically evaluate GPT-4's performance across images, videos, and point clouds, using 16 benchmark datasets to measure top-1 and top-5 accuracy. Our findings show that GPT-4, enhanced with rich linguistic descriptions, significantly improves zero-shot recognition, offering an average top-1 accuracy increase of 7% across all datasets. GPT-4 excels in visual recognition, outshining OpenAI-CLIP's ViT-L and rivaling EVA-CLIP's ViT-E, particularly in video datasets HMDB-51 and UCF-101, where it leads by 22% and 9%, respectively. We hope this research contributes valuable data points and experience for future studies. We release our code at https://github.com/whwu95/GPT4Vis.
title GPT4Vis: What Can GPT-4 Do for Zero-shot Visual Recognition?
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2311.15732