ColorMAE：探索掩码自编码器中的数据无关掩码策略
ColorMAE: Exploring data-independent masking strategies in Masked AutoEncoders
AI总结：
ColorMAE 提出一种数据无关的掩码生成方法，通过过滤随机噪声产生多种掩码模式，无需额外参数或计算，显著提升 MAE 下游任务性能，语义分割 mIoU 提升 2.72。
摘要：
掩码自编码器（MAE）已成为一种强大的自监督框架，在广泛的下游任务中展现出卓越的性能。为了增加 pretext 任务的难度并学习更丰富的视觉表征，现有工作集中于用更复杂的策略替代标准随机掩码，例如对抗引导和教师引导的掩码。然而，这些策略依赖于输入数据，因此通常会增加模型复杂度，并需要额外的计算来生成掩码模式。这引发了一个问题：我们能否在不依赖输入数据或产生额外计算成本的情况下，超越随机掩码来提升 MAE 的性能？在这项工作中，我们引入了一种简单而有效的数据无关方法，称为 ColorMAE，它通过过滤随机噪声来生成不同的二值掩码模式。受图像处理中彩色噪声的启发，我们探索了四种类型的滤波器，以产生具有不同空间和语义先验的掩码模式。ColorMAE 在网络中不需要额外的可学习参数或计算开销，却显著增强了学习到的表征。我们提供了全面的实证评估，证明了我们的策略在下游任务中相对于随机掩码的优越性。值得注意的是，我们报告了在语义分割任务中，相对于基线 MAE 实现，mIoU 提升了 2.72。
英文摘要：
Masked AutoEncoders (MAE) have emerged as a robust self-supervised framework, offering remarkable performance across a wide range of downstream tasks. To increase the difficulty of the pretext task and learn richer visual representations, existing works have focused on replacing standard random masking with more sophisticated strategies, such as adversarial-guided and teacher-guided masking. However, these strategies depend on the input data thus commonly increasing the model complexity and requiring additional calculations to generate the mask patterns. This raises the question: Can we enhance MAE performance beyond random masking without relying on input data or incurring additional computational costs? In this work, we introduce a simple yet effective data-independent method, termed ColorMAE, which generates different binary mask patterns by filtering random noise. Drawing inspiration from color noise in image processing, we explore four types of filters to yield mask patterns with different spatial and semantic priors. ColorMAE requires no additional learnable parameters or computational overhead in the network, yet it significantly enhances the learned representations. We provide a comprehensive empirical evaluation, demonstrating our strategy's superiority in downstream tasks compared to random masking. Notably, we report an improvement of 2.72 in mIoU in semantic segmentation tasks relative to baseline MAE implementations.
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。
