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：掩码自编码器通过随机屏蔽图像块并进行重建，已在多种视觉任务中展现出卓越性能。然而，与对比学习中数据增强作为核心环节不同，针对掩码自编码器的有效数据增强策略仍属开放问题。本文研究了适用于掩码自编码器的混合增强方法。我们首先证明，由于互信息的增加，简单混合反而会降低模型性能。为解决该问题，我们提出同源识别——一种辅助预文本任务，不仅通过明确要求每个块识别同源块来缓解互信息增长，还能进行面向物体的自监督预训练以提升下游密集感知性能。通过大量实验，我们证明提出的混合自编码器在不同下游任务中，作为掩码图像建模增强方法取得了最先进的迁移结果，且效率显著。具体而言，采用标准ViT-Base骨干时，我们的混合自编码器在ImageNet-1K、ADE20K和COCO上分别以+0.3%准确率、+1.7 mIoU和+0.9 AP超越原始掩码自编码器。此外，混合自编码器在训练速度提升2倍的同时，超越了结合实例判别的强掩码图像建模方法iBOT。据我们所知，这是首个从预文本任务设计角度，针对掩码图像建模提出混合方法的工作。代码将开源。