Large language models are built on top of a transformer-based architecture to process textual inputs. For example, the LLaMA stands out among many open-source implementations. Can the same transformer be used to process 2D images? In this paper, we answer this question by unveiling a LLaMA-like vision transformer in plain and pyramid forms, termed VisionLLaMA, which is tailored for this purpose. VisionLLaMA is a unified and generic modelling framework for solving most vision tasks. We extensively evaluate its effectiveness using typical pre-training paradigms in a good portion of downstream tasks of image perception and especially image generation. In many cases, VisionLLaMA have exhibited substantial gains over the previous state-of-the-art vision transformers. We believe that VisionLLaMA can serve as a strong new baseline model for vision generation and understanding. Our code is released at https://github.com/Meituan-AutoML/VisionLLaMA.
@article{arxiv.2403.00522,
title = {VisionLLaMA: A Unified LLaMA Backbone for Vision Tasks},
author = {Xiangxiang Chu and Jianlin Su and Bo Zhang and Chunhua Shen},
journal= {arXiv preprint arXiv:2403.00522},
year = {2024}
}