用OpenFlamingo分析120万二手车零件帖子，发现模型可识别模式但需适配数据。
Leveraging OpenFlamingo for Multimodal Embedding Analysis of C2C Car Parts Data
- 用OpenFlamingo提取图文联合嵌入，结合聚类分析帖子内在模式。
- 120万条数据中多数聚类呈现规律性，部分无明显内部结构。
- 适合做多模态数据挖掘，尤其对电商或二手交易场景有参考价值。
本文研究多模态机器学习模型，特别是OpenFlamingo，在处理大规模消费者对消费者（C2C）汽车零部件在线帖子数据方面的表现。我们从OfferUp和Craigslist两个平台收集了超过120万条含图文的帖子数据。采用OpenFlamingo模型提取每条帖子的文本与图像嵌入，并对联合嵌入进行k-means聚类，以发现帖子间的潜在模式与共性。结果显示，大多数聚类具有明显模式，但部分聚类内部无显著结构。该结果表明，OpenFlamingo可用于大规模数据中的模式发现，但需根据具体数据集调整模型架构。
原文摘要 · Abstract (English)
In this paper, we aim to investigate the capabilities of multimodal machine learning models, particularly the OpenFlamingo model, in processing a large-scale dataset of consumer-to-consumer (C2C) online posts related to car parts. We have collected data from two platforms, OfferUp and Craigslist, resulting in a dataset of over 1.2 million posts with their corresponding images. The OpenFlamingo model was used to extract embeddings for the text and image of each post. We used $k$-means clustering on the joint embeddings to identify underlying patterns and commonalities among the posts. We have found that most clusters contain a pattern, but some clusters showed no internal patterns. The results provide insight into the fact that OpenFlamingo can be used for finding patterns in large datasets but needs some modification in the architecture according to the dataset.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。