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

Reported on 4 benchmarks across 2 tasks · 1 paper · 2 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 (val)· 2022-10-20
63.2
SOTA
Towards Sustainable Self-supervised Learning arXiv:2210.11016
Semantic SegmentationonImageNet-S
mIoU (test)· 2022-10-20
62.5
best: 63.3 (SERE (ViT-B/16, 100ep, 224x224, SSL+FT))
Towards Sustainable Self-supervised Learning arXiv:2210.11016

Audio2 results

10-shot image generationonImageNet-S
mIoU (val)· 2022-10-20
63.2
SOTA
Towards Sustainable Self-supervised Learning arXiv:2210.11016
10-shot image generationonImageNet-S
mIoU (test)· 2022-10-20
62.5
best: 63.3 (SERE (ViT-B/16, 100ep, 224x224, SSL+FT))
Towards Sustainable Self-supervised Learning arXiv:2210.11016