ColorMAE: Exploring data-independent masking strategies in Masked AutoEncoders
Open paper
Benchmark
Model
Rank
Results
semantic-segmentation-on-ade20k
ColorMAE-Green-ViTB-1600
#146
Validation mIoU: 49.3
image-classification-on-imagenet
ColorMAE-Green-ViTB-1600
#420
Top 1 Accuracy: 83.8%
Rank counts only results with a code link.