Papers › ColorMAE: Exploring data-independent masking strategies in Masked AutoEncoders

ColorMAE: Exploring data-independent masking strategies in Masked AutoEncoders

17 Jul 2024arXiv:2407.13036archive 2025-07-28

Carlos Hinojosa, Shuming Liu, Bernard Ghanem

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.

PaperPDFCode

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

carlosh93/ColorMAE officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image ClassificationInstance SegmentationObject DetectionSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet ColorMAE-Green-ViTB-1600 Top 1 Accuracy 83.8% #387 of 1060 Archive leaderboard report
Instance Segmentation COCO ColorMAE-Green-ViTB-1600 maskAP 44.4 #1 of 1 Archive leaderboard report
Instance Segmentation COCO ColorMAE-Green-ViTB-1600 maskAP50 67.8 #1 of 1 Archive leaderboard report
Instance Segmentation COCO ColorMAE-Green-ViTB-1600 maskAP75 48 #1 of 1 Archive leaderboard report
Object Detection COCO ColorMAE-Green-ViTB-1600 boxAP 50.1 #1 of 1 Archive leaderboard report
Object Detection COCO ColorMAE-Green-ViTB-1600 boxAP50 70.7 #1 of 1 Archive leaderboard report
Object Detection COCO ColorMAE-Green-ViTB-1600 boxAP75 54.7 #1 of 1 Archive leaderboard report
Semantic Segmentation ADE20K ColorMAE-Green-ViTB-1600 Validation mIoU 49.3 #135 of 235 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

MAE

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections