SupMAE：有监督掩码自编码器是高效的视觉学习器
SupMAE: Supervised Masked Autoencoders Are Efficient Vision Learners
AI总结：
本文提出SupMAE，通过有监督分类分支将MAE扩展到全监督设置并仅用可见图像块分类，以30%计算量达到与MAE相当的ImageNet性能，且鲁棒性和迁移性更优。
摘要：
近来，自监督掩码自编码器（MAE）因其出色的表征学习能力受到前所未有的关注。然而，其预训练任务掩码图像建模（MIM）通过重建缺失的局部图像块进行学习，缺乏对图像的全局理解。本文通过增加一个有监督分类分支，将MAE扩展到完全有监督设置，从而使MAE能够利用黄金标签有效学习全局特征。所提出的Supervised MAE（SupMAE，有监督掩码自编码器）仅利用可见的图像块子集进行分类，而不同于使用全部图像块的标准有监督预训练。实验表明，SupMAE不仅训练效率更高，而且能学习到更鲁棒、更具可迁移性的特征。具体而言，在ImageNet上使用ViT-B/16模型评估时，SupMAE仅用30%的计算量便取得了与MAE相当的性能。SupMAE在ImageNet变体上的鲁棒性以及迁移学习性能优于MAE和标准有监督预训练对照方法。代码位于https://github.com/enyac-group/supmae。
英文摘要：
Recently, self-supervised Masked Autoencoders (MAE) have attracted unprecedented attention for their impressive representation learning ability. However, the pretext task, Masked Image Modeling (MIM), reconstructs the missing local patches, lacking the global understanding of the image. This paper extends MAE to a fully supervised setting by adding a supervised classification branch, thereby enabling MAE to learn global features from golden labels effectively. The proposed Supervised MAE (SupMAE) only exploits a visible subset of image patches for classification, unlike the standard supervised pre-training where all image patches are used. Through experiments, we demonstrate that SupMAE is not only more training efficient but it also learns more robust and transferable features. Specifically, SupMAE achieves comparable performance with MAE using only 30% of compute when evaluated on ImageNet with the ViT-B/16 model. SupMAE's robustness on ImageNet variants and transfer learning performance outperforms MAE and standard supervised pre-training counterparts. Codes are available at https://github.com/enyac-group/supmae.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
