CASIA OpenIR  > 学术期刊  > Machine Intelligence Research
How Good is Google Bard's Visual Understanding? An Empirical Study on Open Challenges
Haotong Qin1;  Ge-Peng Ji2; Salman Khan3; Deng-Ping Fan1; Fahad Shahbaz Khan3; Luc Van Gool1
Source PublicationMachine Intelligence Research
ISSN2731-538X
2023
Volume20Issue:5Pages:605-613
Abstract

Google's Bard has emerged as a formidable competitor to OpenAI's ChatGPT in the field of conversational AI. Notably, Bard has recently been updated to handle visual inputs alongside text prompts during conversations. Given Bard's impressive track record in handling textual inputs, we explore its capabilities in understanding and interpreting visual data (images) conditioned by text questions. This exploration holds the potential to unveil new insights and challenges for Bard and other forthcoming multi-modal Gener ative models, especially in addressing complex computer vision problems that demand accurate visual and language understanding. Specifically, in this study, we focus on 15 diverse task scenarios encompassing regular, camouflaged, medical, under-water and remote sensing data to comprehensively evaluate Bard's performance. Our primary finding indicates that Bard still struggles in these vision scenarios, highlighting the significant gap in vision-based understanding that needs to be bridged in future developments. We expect that this empirical study will prove valuable in advancing future models, leading to enhanced capabilities in comprehending and interpreting fine grained visual data. Our project is released on https://github.com/htqin/GoogleBard-VisUnderstand.

KeywordGoogle Bard, multi-modal understanding, visual comprehension, large language models, conversational AI, chatbot
DOI10.1007/s11633-023-1469-x
Sub direction classification其他
planning direction of the national heavy laboratory其他
Paper associated data
Chinese guidehttps://mp.weixin.qq.com/s/zRrjXKl7hhEjeD1nVI0PVQ
Citation statistics
Cited Times:1[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/55998
Collection学术期刊_Machine Intelligence Research
Affiliation1.Computer Vision Lab (CVL), ETH Zürich, Zürich 8001, Switzerland
2.College of Engineering, Computing & Cybernetics, Australian National University, Canberra 8105, Australia
3.Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi 999041, UAE
Recommended Citation
GB/T 7714
Haotong Qin, Ge-Peng Ji,Salman Khan,et al. How Good is Google Bard's Visual Understanding? An Empirical Study on Open Challenges[J]. Machine Intelligence Research,2023,20(5):605-613.
APA Haotong Qin, Ge-Peng Ji,Salman Khan,Deng-Ping Fan,Fahad Shahbaz Khan,&Luc Van Gool.(2023).How Good is Google Bard's Visual Understanding? An Empirical Study on Open Challenges.Machine Intelligence Research,20(5),605-613.
MLA Haotong Qin,et al."How Good is Google Bard's Visual Understanding? An Empirical Study on Open Challenges".Machine Intelligence Research 20.5(2023):605-613.
Files in This Item: Download All
File Name/Size DocType Version Access License
MIR-2023-08-155.pdf(10373KB)期刊论文出版稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Haotong Qin]'s Articles
[ Ge-Peng Ji]'s Articles
[Salman Khan]'s Articles
Baidu academic
Similar articles in Baidu academic
[Haotong Qin]'s Articles
[ Ge-Peng Ji]'s Articles
[Salman Khan]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Haotong Qin]'s Articles
[ Ge-Peng Ji]'s Articles
[Salman Khan]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: MIR-2023-08-155.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.