Zihang Li

MiERDCIR: Intent-Diverse Synthetic Rewriting for Generalizable Composed Image Retrieval; with an Analysis of Instance-aware Soft Contrastive Learning

Composed Image Retrieval (CIR) asks a system to retrieve a target image from a reference image and a natural-language modification. Although large vision-language models provide strong global image-text representations, CIR remains difficult because training data often contains verbose or weakly pragmatic modification...