Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Multi-Label Classification for Fashion Data: Zero-Shot Classifiers via Few-Shot Learning on Large Language Models

Topics: Applications of Knowledge Discovery and Information Retrieval; Clustering and Classification Methods; Context Discovery; Deep Learning; Information Extraction; Machine Learning; Neural Networks; Statistical Methods

Authors: Dongming Jiang ; Abhishek Shah ; Stanley Yeung ; Jessica Zhu ; Karan Singh and George Goldenberg

Affiliation: CaaStle Inc, U.S.A.

Keyword(s): Large Language Model, Few-Shot Learning, Zero-Shot Learning, Inference, Knowledge Generation, Multi-Label Classification, Scalability, Fashion Dynamics.

Abstract: Multi-Label classification is essential in the fashion industry due to the complexity of fashion items, which often have multiple attributes such as style, material, and occasion. Traditional machine-learning approaches face challenges like data imbalance, high dimensionality, and the constant emergence of new styles and labels. To address these issues, we propose a novel approach that leverages Large Language Models (LLMs) by integrating few-shot and zero-shot learning. Our methodology utilizes LLMs to perform few-shot learning on a small, labeled dataset, generating precise descriptions of new fashion classes. These descriptions guide the zero-shot learning process, allowing for the classification of new items and categories with minimal labeled data. We demonstrate this approach using OpenAI’s GPT-4, a state-of-the-art LLM. Experiments on a dataset from CaaStle Inc., containing 2,480 unique styles with multiple labels, show significant improvements in classification performance. F ew-shot learning enhances the quality of zero-shot classifiers, leading to superior results. GPT-4’s multi-modal capabilities further improve the system’s effectiveness. Our approach provides a scalable, flexible, and accurate solution for fashion classification, adapting to dynamic trends with minimal data requirements, thereby improving operational efficiency and customer experience. Additionally, this method is highly generalizable and can be applied beyond the fashion industry. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.133.79.80

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Jiang, D., Shah, A., Yeung, S., Zhu, J., Singh, K. and Goldenberg, G. (2024). Multi-Label Classification for Fashion Data: Zero-Shot Classifiers via Few-Shot Learning on Large Language Models. In Proceedings of the 16th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - KDIR; ISBN 978-989-758-716-0; ISSN 2184-3228, SciTePress, pages 250-257. DOI: 10.5220/0012899100003838

@conference{kdir24,
author={Dongming Jiang and Abhishek Shah and Stanley Yeung and Jessica Zhu and Karan Singh and George Goldenberg},
title={Multi-Label Classification for Fashion Data: Zero-Shot Classifiers via Few-Shot Learning on Large Language Models},
booktitle={Proceedings of the 16th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - KDIR},
year={2024},
pages={250-257},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012899100003838},
isbn={978-989-758-716-0},
issn={2184-3228},
}

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - KDIR
TI - Multi-Label Classification for Fashion Data: Zero-Shot Classifiers via Few-Shot Learning on Large Language Models
SN - 978-989-758-716-0
IS - 2184-3228
AU - Jiang, D.
AU - Shah, A.
AU - Yeung, S.
AU - Zhu, J.
AU - Singh, K.
AU - Goldenberg, G.
PY - 2024
SP - 250
EP - 257
DO - 10.5220/0012899100003838
PB - SciTePress