Neighbor-aware Instance Refining for Cross-Modal Retrieval with Noisy Labels

This paper addresses the problem of noisy labels in cross-modal retrieval, a common issue in multi-modal data analysis. It proposes a novel framework, NIRNL, to improve retrieval performance by refining instances based on neighborhood consensus and tailored optimization strategies. The key contribution is the ability to handle noisy data effectively and achieve state-of-the-art results.