GranViT: A Fine-Grained Vision Model With Autoregressive Perception For MLLMs

TL;DR

GranViT introduces a fine-grained vision transformer trained on a large annotated dataset, enhancing regional perception and reasoning in multi-modal large language models, leading to state-of-the-art results in various vision-language tasks.

Contribution

The paper presents GranViT, a novel vision transformer with a large-scale fine-grained pretraining dataset and a new training framework that improves regional perception in MLLMs.

Findings

Outperforms existing vision encoders in fine-grained recognition.

Achieves state-of-the-art results in multimodal VQA.

Enhances OCR understanding and localization capabilities.

Abstract

Vision encoders are indispensable for allowing impressive performance of Multi-modal Large Language Models (MLLMs) in vision language tasks such as visual question answering and reasoning. However, existing vision encoders focus on global image representations but overlook fine-grained regional analysis. They are limited in fine grained perception due to the scarcity of fine grained annotated data and the lack of a fine grained pre-training paradigm. In this paper, we propose GranViT, a novel Vision Transformer that integrates fine-grained feature extraction with semantic alignment to Large Language Models (LLMs) via region level autoregressive training. We first construct Gran-29M, a dataset comprising 2million natural and OCR images paired with over 180 million high-quality region-level annotations, to enable large scale fine grained pretraining. Consequently, we develop a pretraining-adaptation framework along with a self distillation mechanism to train fine-grained GranViT on Gran-29M. We sufficiently exploit the fine-grained annotations from Gran-29M to resort to bounding-box-to-caption regression to enhance localized visual representation of the vision encoder in the pretraining and caption-to-bounding-box regression to improve vision feature utilization and localization for LLM in the adaptation. We further incorporate a self distillation mechanism that imposes explicit localization constraints on the vision encoder to strengthen its regional reasoning capability. Extensive experiments show that GranViT surpasses existing vision encoders and attains strong transferability to varying LLMs. Remarkably, it achieves state-of-the-art results on fine-grained recognition, multimodal VQA, and OCR understanding.