Context-I2W: Mapping Images to Context-dependent Words for Accurate Zero-Shot Composed Image Retrieval

TL;DR

This paper introduces Context-I2W, a novel method for zero-shot composed image retrieval that adaptively maps images to context-dependent pseudo-word tokens, significantly improving accuracy across diverse manipulation tasks without extra supervision.

Contribution

The paper proposes a new context-dependent mapping network, Context-I2W, which enhances zero-shot image retrieval by adaptively converting images into pseudo-word tokens tailored to specific manipulation tasks.

Findings

Achieves state-of-the-art results on four ZS-CIR tasks.

Boosts performance by 1.88% to 3.60% over previous methods.

Demonstrates strong generalization without extra supervision.

Abstract

Different from Composed Image Retrieval task that requires expensive labels for training task-specific models, Zero-Shot Composed Image Retrieval (ZS-CIR) involves diverse tasks with a broad range of visual content manipulation intent that could be related to domain, scene, object, and attribute. The key challenge for ZS-CIR tasks is to learn a more accurate image representation that has adaptive attention to the reference image for various manipulation descriptions. In this paper, we propose a novel context-dependent mapping network, named Context-I2W, for adaptively converting description-relevant Image information into a pseudo-word token composed of the description for accurate ZS-CIR. Specifically, an Intent View Selector first dynamically learns a rotation rule to map the identical image to a task-specific manipulation view. Then a Visual Target Extractor further captures local information covering the main targets in ZS-CIR tasks under the guidance of multiple learnable queries. The two complementary modules work together to map an image to a context-dependent pseudo-word token without extra supervision. Our model shows strong generalization ability on four ZS-CIR tasks, including domain conversion, object composition, object manipulation, and attribute manipulation. It obtains consistent and significant performance boosts ranging from 1.88% to 3.60% over the best methods and achieves new state-of-the-art results on ZS-CIR. Our code is available at https://github.com/Pter61/context-i2w.