Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Scalable Pre-training of Large Autoregressive Image Models

About

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% on ImageNet-1k with a frozen trunk. Interestingly, even at 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.

Alaaeldin El-Nouby, Michal Klein, Shuangfei Zhai, Miguel Angel Bautista, Alexander Toshev, Vaishaal Shankar, Joshua M Susskind, Armand Joulin• 2024

Related benchmarks

TaskDatasetResultRank
Semantic segmentationADE20K
mIoU29.59
1028
Image ClassificationCIFAR-100
Accuracy91.8
691
Semantic segmentationCityscapes
mIoU27.05
668
Image ClassificationStanford Cars
Accuracy95
660
Image ClassificationImageNet-1K--
600
Image ClassificationFood-101
Accuracy94.1
570
Image ClassificationEuroSAT
Accuracy98.6
569
Image ClassificationCIFAR-10
Accuracy98.9
564
Image ClassificationOxford-IIIT Pets
Accuracy95.4
378
Image ClassificationiNaturalist 2018
Top-1 Accuracy75.5
291
Showing 10 of 33 rows

Other info

Code

Follow for update