Zero-shot Composed Text-Image Retrieval
This work addresses the challenge of improving user expression ability in image retrieval by enabling zero-shot composed retrieval, which is incremental as it builds on existing CIR methods with automated data construction and a novel fusion mechanism.
The paper tackles the problem of composed image retrieval (CIR) by proposing a scalable pipeline to automatically construct training datasets from image-text pairs and introducing a transformer-based adaptive aggregation model, TransAgg, which achieves performance on par with or significantly outperforms existing state-of-the-art models in zero-shot scenarios on benchmarks like CIRR and FashionIQ.
In this paper, we consider the problem of composed image retrieval (CIR), it aims to train a model that can fuse multi-modal information, e.g., text and images, to accurately retrieve images that match the query, extending the user's expression ability. We make the following contributions: (i) we initiate a scalable pipeline to automatically construct datasets for training CIR model, by simply exploiting a large-scale dataset of image-text pairs, e.g., a subset of LAION-5B; (ii) we introduce a transformer-based adaptive aggregation model, TransAgg, which employs a simple yet efficient fusion mechanism, to adaptively combine information from diverse modalities; (iii) we conduct extensive ablation studies to investigate the usefulness of our proposed data construction procedure, and the effectiveness of core components in TransAgg; (iv) when evaluating on the publicly available benckmarks under the zero-shot scenario, i.e., training on the automatically constructed datasets, then directly conduct inference on target downstream datasets, e.g., CIRR and FashionIQ, our proposed approach either performs on par with or significantly outperforms the existing state-of-the-art (SOTA) models. Project page: https://code-kunkun.github.io/ZS-CIR/