Scalable Pre-training of Large Autoregressive Image Models
CoRR(2024)
摘要
This paper introduces AIM, a collection of vision models pre-trained with an
autoregressive objective. These models are inspired by their textual
counterparts, i.e., Large Language Models (LLMs), and exhibit similar scaling
properties. Specifically, we highlight two key findings: (1) the performance of
the visual features scale with both the model capacity and the quantity of
data, (2) the value of the objective function correlates with the performance
of the model on downstream tasks. We illustrate the practical implication of
these findings by pre-training a 7 billion parameter AIM on 2 billion images,
that achieves 84.0
this scale, we observe no sign of saturation in performance, suggesting that
AIM potentially represents a new frontier for training large-scale vision
models. The pre-training of AIM is similar to the pre-training of LLMs, and
does not require any image-specific strategy to stabilize the training at
scale.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要