从像素到分量：用于视觉表示学习的特征向量掩蔽
From Pixels to Components: Eigenvector Masking for Visual Representation Learning
AI总结：
针对随机像素块掩蔽无法学习有意义高级特征的问题，提出基于主成分分析的特征向量掩蔽策略，通过掩蔽占固定方差比例的分量并重建，提升图像分类性能，为视觉表示学习提供鲁棒替代方案。
摘要：
通过图像的可见部分预测被掩蔽部分是视觉表示学习中一种强大的自监督方法。然而，掩蔽随机像素块的常见做法存在某些失效模式，可能阻碍学习下游任务所需的有意义的高级特征。我们提出一种替代掩蔽策略，其作用于数据的适当变换而非原始像素。具体而言，我们执行主成分分析，然后随机掩蔽占固定数据方差比例的部分分量子集。学习任务随后转化为从可见分量重建被掩蔽分量。与局部像素块相比，图像的主成分携带更多全局信息。因此我们假设，通过可见分量预测被掩蔽分量涉及更多高级特征，使我们的掩蔽策略能提取更有用的表示。这得到我们实证结果的支持，该结果表明分量掩蔽在图像分类性能上优于像素掩蔽。我们的方法因此构成传统掩蔽图像建模方法的一种简单且鲁棒的数据驱动替代方案。
英文摘要：
Predicting masked from visible parts of an image is a powerful self-supervised approach for visual representation learning. However, the common practice of masking random patches of pixels exhibits certain failure modes, which can prevent learning meaningful high-level features, as required for downstream tasks. We propose an alternative masking strategy that operates on a suitable transformation of the data rather than on the raw pixels. Specifically, we perform principal component analysis and then randomly mask a subset of components, which accounts for a fixed ratio of the data variance. The learning task then amounts to reconstructing the masked components from the visible ones. Compared to local patches of pixels, the principal components of images carry more global information. We thus posit that predicting masked from visible components involves more high-level features, allowing our masking strategy to extract more useful representations. This is corroborated by our empirical findings which demonstrate improved image classification performance for component over pixel masking. Our method thus constitutes a simple and robust data-driven alternative to traditional masked image modeling approaches.
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。
