Air-know: Arbiter-calibrated Knowledge-internalizing Robust Network For Composed Image Retrieval

Abstract

Composed Image Retrieval (CIR) has attracted significant attention due to its flexible multimodal query method, yet its development is severely constrained by the Noisy Triplet Correspondence (NTC) problem. Most existing robust learning methods rely on the "small loss hypothesis", but the unique semantic ambiguity in NTC, such as "partial matching", invalidates this assumption, leading to unreliable noise identification. This entraps the model in a self dependent vicious cycle where the learner is intertwined with the arbiter, ultimately causing catastrophic "representation pollution". To address this critical challenge, we propose a novel "Expert-Proxy-Diversion" decoupling paradigm, named Air-Know (ArbIteR calibrated Knowledge iNternalizing rObust netWork). Air-Know incorporates three core modules: (1) External Prior Arbitration (EPA), which utilizes Multimodal Large Language Models (MLLMs) as an offline expert to construct a high precision anchor dataset; (2) Expert Knowledge Intern

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyfu2026air

Related papers

• INTENT: Invariance And Discrimination-aware Noise Mitigation For Robust Composed Image Retrieval (2026)0.00
• HABIT: Chrono-synergia Robust Progressive Learning Framework For Composed Image Retrieval (2026)2.35
• Conesep: Cone-based Robust Noise-unlearning Compositional Network For Composed Image Retrieval (2026)0.00
• NCL-CIR: Noise-aware Contrastive Learning For Composed Image Retrieval (2025)2.26
• HINT: Composed Image Retrieval With Dual-path Compositional Contextualized Network (2026)0.78
• Collaborative Group: Composed Image Retrieval Via Consensus Learning From Noisy Annotations (2023)0.00
• Heterogeneous Uncertainty-guided Composed Image Retrieval With Fine-grained Probabilistic Learning (2026)0.00
• CSMCIR: Cot-enhanced Symmetric Alignment With Memory Bank For Composed Image Retrieval (2026)0.00