Knowledge-Enhanced Dual-stream Zero-shot Composed Image Retrieval

arXiv:2403.16005v1 Announce Type: new
Abstract: We study the zero-shot Composed Image Retrieval (ZS-CIR) task, which is to retrieve the target image given a reference image and a description without training on the triplet datasets. Previous works generate pseudo-word tokens by projecting the reference image features to the text embedding space. However, they focus on the global visual representation, ignoring the representation of detailed attributes, e.g., color, object number and layout. To address this challenge, we propose a Knowledge-Enhanced Dual-stream zero-shot …

abstract arxiv cs.cv datasets embedding features focus generate however image knowledge reference retrieval space study text text embedding tokens training type word zero-shot