GPT-4o mini与Gemini 2.0 Flash能否预测细粒度时尚产品属性？一项零样本分析
Can GPT-4o mini and Gemini 2.0 Flash Predict Fine-Grained Fashion Product Attributes? A Zero-Shot Analysis
AI总结：
本研究针对细粒度时尚属性识别任务，在DeepFashion-MultiModal数据集上对GPT-4o-mini和Gemini 2.0 Flash开展零样本评估，发现Gemini 2.0 Flash表现更优，为电商属性标注落地和领域微调提供参考。
摘要：
时尚零售业务的核心是产品理解能力。产品属性标注可根据业务流程辅助产品理解。高质量的属性标注能提升消费者在零售网站数百万件商品中浏览时的体验，还能构建条理清晰的产品目录，最终直接影响消费者的“发现体验”。尽管大语言模型（LLM）在多模态数据理解方面已展现出卓越能力，但它们在细粒度时尚属性识别任务上的表现仍有待充分探究。\n本文对兼顾性能、速度与成本效率的前沿大语言模型——主要是GPT-4o-mini和Gemini 2.0 Flash——开展零样本评估。研究采用DeepFashion-MultiModal数据集（https://github.com/yumingj/DeepFashion-MultiModal），在仅以图像作为唯一产品信息输入的约束环境下，针对时尚产品属性标注任务评估上述模型，覆盖18类时尚属性，明确了两类模型的优势领域。\n分析结果显示，Gemini 2.0 Flash整体表现最优，所有属性的宏F1得分为56.79%；GPT-4o-mini的宏F1得分为43.28%。通过详细的误差分析，本研究为将这类大语言模型部署到电商生产环境的产品属性相关任务提供了实践参考，同时凸显了领域专属微调方法的必要性，也为时尚人工智能与多模态属性提取领域的后续研究奠定了基础。
英文摘要：
The fashion retail business is centered around the capacity to comprehend products. Product attribution helps in comprehending products depending on the business process. Quality attribution improves the customer experience as they navigate through millions of products offered by a retail website. It leads to well-organized product catalogs. In the end, product attribution directly impacts the 'discovery experience' of the customer. Although large language models (LLMs) have shown remarkable capabilities in understanding multimodal data, their performance on fine-grained fashion attribute recognition remains under-explored. This paper presents a zero-shot evaluation of state-of-the-art LLMs that balance performance with speed and cost efficiency, mainly GPT-4o-mini and Gemini 2.0 Flash. We have used the dataset DeepFashion-MultiModal (https://github.com/yumingj/DeepFashion-MultiModal) to evaluate these models in the attribution tasks of fashion products. Our study evaluates these models across 18 categories of fashion attributes, offering insight into where these models excel. We only use images as the sole input for product information to create a constrained environment. Our analysis shows that Gemini 2.0 Flash demonstrates the strongest overall performance with a macro F1 score of 56.79% across all attributes, while GPT-4o-mini scored a macro F1 score of 43.28%. Through detailed error analysis, our findings provide practical insights for deploying these LLMs in production e-commerce product attribution-related tasks and highlight the need for domain-specific fine-tuning approaches. This work also lays the groundwork for future research in fashion AI and multimodal attribute extraction.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
