MAE (ViT-B/16, 224x224, SSL+FT, mmseg)

Reported on 4 benchmarks across 2 tasks · 1 paper · 4 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Medical2 results

Semantic SegmentationonImageNet-S
mIoU (test)· 2021-11-11
61.2
best: 63.3 (SERE (ViT-B/16, 100ep, 224x224, SSL+FT))
SOTA
Masked Autoencoders Are Scalable Vision Learners arXiv:2111.06377
Semantic SegmentationonImageNet-S
mIoU (val)· 2021-11-11
61.6
best: 63.2 (TEC (ViT-B/16, 224x224, SSL+FT, mmseg))
SOTA
Masked Autoencoders Are Scalable Vision Learners arXiv:2111.06377

Audio2 results

10-shot image generationonImageNet-S
mIoU (test)· 2021-11-11
61.2
best: 63.3 (SERE (ViT-B/16, 100ep, 224x224, SSL+FT))
SOTA
Masked Autoencoders Are Scalable Vision Learners arXiv:2111.06377
10-shot image generationonImageNet-S
mIoU (val)· 2021-11-11
61.6
best: 63.2 (TEC (ViT-B/16, 224x224, SSL+FT, mmseg))
SOTA
Masked Autoencoders Are Scalable Vision Learners arXiv:2111.06377