Masked Autoencoder (MAE) has demonstrated superior performance on various vision tasks via randomly masking image patches and reconstruction. However, effective data augmentation strategies for MAE still remain open questions, different from those in contrastive learning that serve as the most important part. This paper studies the prevailing mixing augmentation for MAE. We first demonstrate that naive mixing will in contrast degenerate model performance due to the increase of mutual information (MI). To address, we propose homologous recognition, an auxiliary pretext task, not only to alleviate the MI increasement by explicitly requiring each patch to recognize homologous patches, but also to perform object-aware self-supervised pre-training for better downstream dense perception performance. With extensive experiments, we demonstrate that our proposed Mixed Autoencoder (MixedAE) achieves the state-of-the-art transfer results among masked image modeling (MIM) augmentations on different downstream tasks with significant efficiency. Specifically, our MixedAE outperforms MAE by +0.3% accuracy, +1.7 mIoU and +0.9 AP on ImageNet-1K, ADE20K and COCO respectively with a standard ViT-Base. Moreover, MixedAE surpasses iBOT, a strong MIM method combined with instance discrimination, while accelerating training by 2x. To our best knowledge, this is the very first work to consider mixing for MIM from the perspective of pretext task design. Code will be made available.

翻译：掩码自编码器（MAE）通过随机掩码图像块并重构，已在多种视觉任务中展现出卓越性能。然而，与对比学习中作为最关键部分的数据增强策略不同，针对MAE的有效数据增强方案仍是一个开放问题。本文研究了面向MAE的主流混合增强方法。我们首先证明，由于互信息的增加，朴素混合反而会降低模型性能。为解决这一问题，我们提出同源识别作为一种辅助预文本任务，不仅通过显式要求每个块识别同源块来缓解互信息增长，还能实现面向目标的自监督预训练，以提升下游密集感知任务的性能。通过大量实验，我们证明所提出的混合自编码器在不同下游任务中达到了掩码图像建模增强方法的最优迁移效果，且显著提升效率。具体而言，在标准ViT-Base架构上，我们的MixedAE在ImageNet-1K、ADE20K和COCO数据集上分别以+0.3%准确率、+1.7 mIoU和+0.9 AP超越MAE。此外，MixedAE在训练速度提升2倍的同时，超越了结合实例判别机制的强MIM方法iBOT。据我们所知，这是首个从预文本任务设计角度考虑MIM混合增强的工作。代码将开源。