AI RESEARCH

ConeSep: Cone-based Robust Noise-Unlearning Compositional Network for Composed Image Retrieval

arXiv CS.CV

ArXi:2604.20358v1 Announce Type: new The Composed Image Retrieval (CIR) task provides a flexible retrieval paradigm via a reference image and modification text, but it heavily relies on expensive and error-prone triplet annotations. This paper systematically investigates the Noisy Triplet Correspondence (NTC) problem