Mosaic: Finding Artistic Connections Across Culture With Conditional Image Retrieval

Abstract

We introduce MosAIc, an interactive web app that allows users to find pairs of semantically related artworks that span different cultures, media, and millennia. To create this application, we introduce Conditional Image Retrieval (CIR) which combines visual similarity search with user supplied filters or "conditions". This technique allows one to find pairs of similar images that span distinct subsets of the image corpus. We provide a generic way to adapt existing image retrieval data-structures to this new domain and provide theoretical bounds on our approach's efficiency. To quantify the performance of CIR systems, we introduce new datasets for evaluating CIR methods and show that CIR performs non-parametric style transfer. Finally, we demonstrate that our CIR data-structures can identify "blind spots" in Generative Adversarial Networks (GAN) where they fail to properly model the true data distribution.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyhamilton2020mosaic

Related papers

• Infocir: Multimedia Analysis For Composed Image Retrieval (2026)1.24
• CSMCIR: Cot-enhanced Symmetric Alignment With Memory Bank For Composed Image Retrieval (2026)0.00
• ICC++: Explainable Image Retrieval For Art Historical Corpora Using Image Composition Canvas (2022)0.00
• Iart: A Search Engine For Art-historical Images To Support Research In The Humanities (2021)8.35
• HINT: Composed Image Retrieval With Dual-path Compositional Contextualized Network (2026)0.78
• Caption-matching: A Multimodal Approach For Cross-domain Image Retrieval (2024)0.00
• TMCIR: Token Merge Benefits Composed Image Retrieval (2025)0.00
• Good4cir: Generating Detailed Synthetic Captions For Composed Image Retrieval (2025)0.00