ColorMAE: Exploring data-independent masking strategies in Masked AutoEncoders

TL;DR

ColorMAE introduces a data-independent masking strategy for Masked AutoEncoders that improves visual representation learning without extra computational costs, outperforming traditional random masking in downstream tasks.

Contribution

We propose ColorMAE, a novel data-independent masking method using color noise filtering, enhancing MAE performance without increasing model complexity.

Findings

Significant improvement in semantic segmentation accuracy (2.72 mIoU)

Outperforms random masking in downstream tasks

No additional computational overhead required

Abstract

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.