AI RESEARCH
Beyond Semantic Search: Towards Referential Anchoring in Composed Image Retrieval
arXiv CS.CV
•
ArXi:2604.05393v1 Announce Type: new Composed Image Retrieval (CIR) has nstrated significant potential by enabling flexible multimodal queries that combine a reference image and modification text. However, CIR inherently prioritizes semantic matching, struggling to reliably retrieve a user-specified instance across contexts. In practice, emphasizing concrete instance fidelity over broad semantics is often consequential. In this work, we propose Object-Anchored Composed Image Retrieval (OACIR), a novel fine-grained retrieval task that mandates strict instance-level consistency.