文献类型： 会议论文

第一作者： Dongming Jiang

作者： Dongming Jiang ¹ ; Abhishek Shah ¹ ; Stanley Yeung ¹ ; Jessica Zhu ¹ ; Karan Singh ¹ ; George Goldenberg ¹ ;

作者机构： 1.CaaStle Inc

关键词： Large language model;Few-Shot learning;Zero-Shot learning;Inference;Knowledge generation;Multi-Label classification;Scalability;Fashion dynamics

会议名称：

主办单位：

页码： 250-257

摘要： 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. Few-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.

分类号： tp391-53