FashionKLIP: Enhancing E-Commerce Image-Text Retrieval with Fashion Multi-Modal Conceptual Knowledge Graph

Image-text retrieval is a core task in the multimodal domain, which arises a lot of attention from both research and industry communities. Recently, the booming of visionlanguage pre-trained (VLP) models has greatly enhanced the performance of cross-modal retrieval. However, the fine-grained interactions between objects from different modalities are far from well-established. This issue becomes more severe in the e-commerce domain, which lacks sufficient training data and fine-grained cross-modal knowledge. To alleviate the problem, this paper proposes a novel e-commerce knowledge-enhanced VLP model FashionKLIP. We first automatically establish a multi-modal conceptual knowledge graph from large-scale e-commerce image-text data, and then inject the prior knowledge into the VLP model to align across modalities at the conceptual level. The experiments conducted on a public benchmark dataset demonstrate that Fash-ionKLIP effectively enhances the performance of e-commerce image-text retrieval upon stateof-the-art VLP models by a large margin. The application of the method in real industrial scenarios also proves the feasibility and efficiency of FashionKLIP. 1