Training-free Zero-shot Composed Image Retrieval with Local Concept Reranking

arXiv:2312.08924v2 Announce Type: replace
Abstract: Composed image retrieval attempts to retrieve an image of interest from gallery images through a composed query of a reference image and its corresponding modified text. It has recently attracted attention due to the collaboration of information-rich images and concise language to precisely express the requirements of target images. Most current composed image retrieval methods follow a supervised learning approach to training on a costly triplet dataset composed of a reference image, modified text, and …

abstract arxiv attention collaboration concept cs.cv express free image images information language query reference requirements retrieval text through training type zero-shot