Learning visual representations is foundational for a broad spectrum of downstream tasks. Although recent vision-language contrastive models, such as CLIP and SigLIP, have achieved impressive zero-shot performance via large-scale vision-language alignment, their reliance on global representations constrains their effectiveness for dense prediction tasks, such as grounding, OCR, and segmentation. To address this gap, we introduce Region-Aware Cluster Discrimination (RICE), a novel method that enhances region-level visual and OCR capabilities. We first construct a billion-scale candidate region dataset and propose a Region Transformer layer to extract rich regional semantics. We further design a unified region cluster discrimination loss that jointly supports object and OCR learning within a single classification framework, enabling efficient and scalable distributed training on large-scale data. Extensive experiments show that RICE consistently outperforms previous methods on tasks, including segmentation, dense detection, and visual perception for Multimodal Large Language Models (MLLMs). The pre-trained models have been released at https://github.com/deepglint/MVT.
@article{arxiv.2507.20025,
title = {Region-based Cluster Discrimination for Visual Representation Learning},
author = {Yin Xie and Kaicheng Yang and Xiang An and Kun Wu and Yongle Zhao and Weimo Deng and Zimin Ran and Yumeng Wang and Ziyong Feng and Roy Miles and Ismail Elezi and Jiankang Deng},
journal= {arXiv preprint arXiv:2507.20025},
year = {2025}
}