ChatGPT-guided Semantics for Zero-shot Learning

Shubho, FH; Chowdhury, TF; Cheraghian, A; Saberi, M; Mohammed, N; Rahman, S

ChatGPT-guided Semantics for Zero-shot Learning

Shubho, FH Chowdhury, TF Cheraghian, A Saberi, M

Mohammed, N Rahman, S

Permalink

Publisher:: IEEE
Publication Type:: Conference Proceeding
Citation:: 2023 International Conference on Digital Image Computing: Techniques and Applications (DICTA), 2024, 00, pp. 418-425
Issue Date:: 2024-01-29

Embargoed

	Filename	Description	Size
	ChatGPT-guided Semantics for Zero-shot Learning.pdf	Accepted version	897.49 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Embargoed
Open Access

This item is currently unavailable due to the publisher's embargo.

The embargo period expires on 29 Jan 2026

Full metadata record

Field	Value	Language
dc.contributor.author	Shubho, FH
dc.contributor.author	Chowdhury, TF
dc.contributor.author	Cheraghian, A
dc.contributor.author	Saberi, M https://orcid.org/0000-0002-5168-2078
dc.contributor.author	Mohammed, N
dc.contributor.author	Rahman, S
dc.date	2023-11-28
dc.date.accessioned	2024-05-20T07:49:49Z
dc.date.available	2024-05-20T07:49:49Z
dc.date.issued	2024-01-29
dc.identifier.citation	2023 International Conference on Digital Image Computing: Techniques and Applications (DICTA), 2024, 00, pp. 418-425
dc.identifier.isbn	979-8-3503-8221-1
dc.identifier.uri	http://hdl.handle.net/10453/179065
dc.description.abstract	Zero shot learning ZSL aims to classify objects that are not observed or seen during training It relies on class semantic description to transfer knowledge from the seen classes to the unseen classes Existing methods of obtaining class semantics include manual attributes or automatic word vectors from language models like word2vec We know attribute annotation is costly whereas automatic word vectors are relatively noisy To address this problem we explore how ChatGPT a large language model can enhance class semantics for ZSL tasks ChatGPT can be a helpful source to obtain text descriptions for each class containing related attributes and semantics We use the word2vec model to get a word vector using the texts from ChatGPT Then we enrich word vectors by combining the word embeddings from class names and descriptions generated by ChatGPT More specifically we leverage ChatGPT to provide extra supervision for the class description eventually benefiting ZSL models We evaluate our approach on various 2D image CUB and AwA and 3D point cloud ModelNet10 ModelNet40 and ScanObjectNN datasets and show that it improves ZSL performance Our work contributes to the ZSL literature by applying ChatGPT for class semantics enhancement and proposing a novel word vector fusion method
dc.language	en
dc.publisher	IEEE
dc.relation.ispartof	2023 International Conference on Digital Image Computing: Techniques and Applications (DICTA)
dc.relation.ispartof	2023 International Conference on Digital Image Computing: Techniques and Applications
dc.relation.isbasedon	10.1109/dicta60407.2023.00064
dc.rights	info:eu-repo/semantics/embargoedAccess
dc.title	ChatGPT-guided Semantics for Zero-shot Learning
dc.type	Conference Proceeding
utslib.citation.volume	00
utslib.location.activity	Port Macquarie, Australia
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
utslib.copyright.status	embargoed	*
utslib.copyright.embargo	2026-01-29T00:00:00+1000Z
dc.date.updated	2024-05-20T07:49:48Z
pubs.finish-date	2023-12-01
pubs.place-of-publication	Piscataway, USA
pubs.publication-status	Published
pubs.start-date	2023-11-28
pubs.volume	00
dc.location	Piscataway, USA

Abstract:

Zero shot learning ZSL aims to classify objects that are not observed or seen during training It relies on class semantic description to transfer knowledge from the seen classes to the unseen classes Existing methods of obtaining class semantics include manual attributes or automatic word vectors from language models like word2vec We know attribute annotation is costly whereas automatic word vectors are relatively noisy To address this problem we explore how ChatGPT a large language model can enhance class semantics for ZSL tasks ChatGPT can be a helpful source to obtain text descriptions for each class containing related attributes and semantics We use the word2vec model to get a word vector using the texts from ChatGPT Then we enrich word vectors by combining the word embeddings from class names and descriptions generated by ChatGPT More specifically we leverage ChatGPT to provide extra supervision for the class description eventually benefiting ZSL models We evaluate our approach on various 2D image CUB and AwA and 3D point cloud ModelNet10 ModelNet40 and ScanObjectNN datasets and show that it improves ZSL performance Our work contributes to the ZSL literature by applying ChatGPT for class semantics enhancement and proposing a novel word vector fusion method

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/179065