AI RESEARCH
INTENT: Invariance and Discrimination-aware Noise Mitigation for Robust Composed Image Retrieval
arXiv CS.CV
•
ArXi:2604.18051v1 Announce Type: new Composed Image Retrieval (CIR) is a challenging image retrieval paradigm that enables to retrieve target images based on multimodal queries consisting of reference images and modification texts. Although substantial progress has been made in recent years, existing methods assume that all samples are correctly matched. However, in real-world scenarios, due to high triplet annotation costs, CIR datasets inevitably contain annotation errors, resulting in incorrectly matched triplets.