English

Efficient Token-Guided Image-Text Retrieval with Consistent Multimodal Contrastive Training

Computer Vision and Pattern Recognition 2023-07-19 v1

Abstract

Image-text retrieval is a central problem for understanding the semantic relationship between vision and language, and serves as the basis for various visual and language tasks. Most previous works either simply learn coarse-grained representations of the overall image and text, or elaborately establish the correspondence between image regions or pixels and text words. However, the close relations between coarse- and fine-grained representations for each modality are important for image-text retrieval but almost neglected. As a result, such previous works inevitably suffer from low retrieval accuracy or heavy computational cost. In this work, we address image-text retrieval from a novel perspective by combining coarse- and fine-grained representation learning into a unified framework. This framework is consistent with human cognition, as humans simultaneously pay attention to the entire sample and regional elements to understand the semantic content. To this end, a Token-Guided Dual Transformer (TGDT) architecture which consists of two homogeneous branches for image and text modalities, respectively, is proposed for image-text retrieval. The TGDT incorporates both coarse- and fine-grained retrievals into a unified framework and beneficially leverages the advantages of both retrieval approaches. A novel training objective called Consistent Multimodal Contrastive (CMC) loss is proposed accordingly to ensure the intra- and inter-modal semantic consistencies between images and texts in the common embedding space. Equipped with a two-stage inference method based on the mixed global and local cross-modal similarity, the proposed method achieves state-of-the-art retrieval performances with extremely low inference time when compared with representative recent approaches.

Keywords

Cite

@article{arxiv.2306.08789,
  title  = {Efficient Token-Guided Image-Text Retrieval with Consistent Multimodal Contrastive Training},
  author = {Chong Liu and Yuqi Zhang and Hongsong Wang and Weihua Chen and Fan Wang and Yan Huang and Yi-Dong Shen and Liang Wang},
  journal= {arXiv preprint arXiv:2306.08789},
  year   = {2023}
}

Comments

Code is publicly available: https://github.com/LCFractal/TGDT

R2 v1 2026-06-28T11:05:28.083Z