Vision-language pre-training (VLP) on large-scale datasets has shown premier performance on various downstream tasks. In contrast to plenty of available benchmarks with English corpus, large-scale pre-training datasets and downstream datasets with Chinese corpus remain largely unexplored. In this work, we build a large-scale high-quality Chinese Cross-Modal Benchmark named CCMB for the research community, which contains the currently largest public pre-training dataset Zero and five human-annotated fine-tuning datasets for downstream tasks. Zero contains 250 million images paired with 750 million text descriptions, plus two of the five fine-tuning datasets are also currently the largest ones for Chinese cross-modal downstream tasks. Along with the CCMB, we also develop a VLP framework named R2D2, applying a pre-Ranking + Ranking strategy to learn powerful vision-language representations and a two-way distillation method (i.e., target-guided Distillation and feature-guided Distillation) to further enhance the learning capability. With the Zero and the R2D2 VLP framework, we achieve state-of-the-art performance on twelve downstream datasets from five broad categories of tasks including image-text retrieval, image-text matching, image caption, text-to-image generation, and zero-shot image classification. The datasets, models, and codes are available at https://github.com/yuxie11/R2D2
CCMB: A Large-scale Chinese Cross-modal Benchmark
A large-scale Chinese cross-modal benchmark and a VLP framework achieve top performance across various vision-language tasks using a pre-Ranking + Ranking strategy and two-way distillation methods.
- Year
- 2022
- Venue
- arXiv 2022
- Authors
- 14
- Hosting
- Abstract onlyARXIV-DEFAULT
Cite
Notes
Only stored in your browser.
Attribution
- Abstract & full text
- arxiv.org/abs/2205.03860v6ARXIV-DEFAULT
- TL;DR
- Semantic Scholar