Self-supervised contrastive learning models, such as CLIP, have set new benchmarks for vision-language models in many downstream tasks. However, their dependency on rigid one-to-one mappings overlooks the complex and often multifaceted relationships between and within texts and images. To this end, we introduce RankCLIP, a novel pre-training method that extends beyond the rigid one-to-one matching framework of CLIP and its variants. By extending the traditional pair-wise loss to list-wise, and leveraging both in-modal and cross-modal ranking consistency, RankCLIP improves the alignment process, enabling it to capture the nuanced many-to-many relationships between and within each modality. Through comprehensive experiments, we demonstrate the effectiveness of RankCLIP in various downstream tasks, notably achieving significant gains in zero-shot classifications over state-of-the-art methods, underscoring the importance of this enhanced learning process.
@article{arxiv.2404.09387,
title = {RankCLIP: Ranking-Consistent Language-Image Pretraining},
author = {Yiming Zhang and Zhuokai Zhao and Zhaorun Chen and Zhili Feng and Zenghui Ding and Yining Sun},
journal= {arXiv preprint arXiv:2404.09387},
year = {2025}
}
Comments
Code and model checkpoints are available at https://github.com/Jam1ezhang/RankCLIP