Fine-Grained Zero-Shot Composed Image Retrieval with Complementary Visual-Semantic Integration

TL;DR

This paper introduces CVSI, a novel zero-shot image retrieval method that effectively captures fine-grained visual and semantic modifications by integrating complementary visual and textual information, outperforming existing methods.

Contribution

CVSI is the first approach to combine visual and semantic information extraction with complementary retrieval for zero-shot composed image retrieval.

Findings

CVSI significantly outperforms state-of-the-art methods on CIRR, CIRCO, and FashionIQ datasets.

The method effectively captures fine-grained modifications in zero-shot scenarios.

Extensive experiments validate the robustness and superiority of CVSI.

Abstract

Zero-shot composed image retrieval (ZS-CIR) is a rapidly growing area with significant practical applications, allowing users to retrieve a target image by providing a reference image and a relative caption describing the desired modifications. Existing ZS-CIR methods often struggle to capture fine-grained changes and integrate visual and semantic information effectively. They primarily rely on either transforming the multimodal query into a single text using image-to-text models or employing large language models for target image description generation, approaches that often fail to capture complementary visual information and complete semantic context. To address these limitations, we propose a novel Fine-Grained Zero-Shot Composed Image Retrieval method with Complementary Visual-Semantic Integration (CVSI). Specifically, CVSI leverages three key components: (1) Visual Information Extraction, which not only extracts global image features but also uses a pre-trained mapping network to convert the image into a pseudo token, combining it with the modification text and the objects most likely to be added. (2) Semantic Information Extraction, which involves using a pre-trained captioning model to generate multiple captions for the reference image, followed by leveraging an LLM to generate the modified captions and the objects most likely to be added. (3) Complementary Information Retrieval, which integrates information extracted from both the query and database images to retrieve the target image, enabling the system to efficiently handle retrieval queries in a variety of situations. Extensive experiments on three public datasets (e.g., CIRR, CIRCO, and FashionIQ) demonstrate that CVSI significantly outperforms existing state-of-the-art methods. Our code is available at https://github.com/yyc6631/CVSI.