Keyword-based Diverse Image Retrieval By Semantics-aware Contrastive Learning And Transformer

Abstract

In addition to relevance, diversity is an important yet less studied performance metric of cross-modal image retrieval systems, which is critical to user experience. Existing solutions for diversity-aware image retrieval either explicitly post-process the raw retrieval results from standard retrieval systems or try to learn multi-vector representations of images to represent their diverse semantics. However, neither of them is good enough to balance relevance and diversity. On the one hand, standard retrieval systems are usually biased to common semantics and seldom exploit diversity-aware regularization in training, which makes it difficult to promote diversity by post-processing. On the other hand, multi-vector representation methods are not guaranteed to learn robust multiple projections. As a result, irrelevant images and images of rare or unique semantics may be projected inappropriately, which degrades the relevance and diversity of the results generated by some typical algorithm

Stats

• citations4
• S2 citations—
• github stars0
• HF likes0
• heat score5.24
• arxiv keyzhao2023keyword

Related papers

• Evaluating Contrastive Models For Instance-based Image Retrieval (2021)5.24
• Tsvc:tripartite Learning With Semantic Variation Consistency For Robust Image-text Retrieval (2025)3.58
• CODER: Coupled Diversity-sensitive Momentum Contrastive Learning For Image-text Retrieval (2022)13.72
• Improving Cross-modal Retrieval With Set Of Diverse Embeddings (2022)13.55
• Vector Retrieval With Similarity And Diversity: How Hard Is It? (2024)0.00
• Simple To Complex Cross-modal Learning To Rank (2017)13.84
• Discriminative Semantic Transitive Consistency For Cross-modal Learning (2021)0.00
• Training Vision Transformers For Image Retrieval (2021)0.00