RF-ConvNext-Tiny (rfmerge, P4, 224x224, SUP)

Reported on 4 benchmarks across 2 tasks · 1 paper

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)· 2022-06-14
51.1
best: 63.3 (SERE (ViT-B/16, 100ep, 224x224, SSL+FT))
RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks arXiv:2206.06637
Semantic SegmentationonImageNet-S
mIoU (val)· 2022-06-14
51.3
best: 63.2 (TEC (ViT-B/16, 224x224, SSL+FT, mmseg))
RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks arXiv:2206.06637

Audio2 results

10-shot image generationonImageNet-S
mIoU (test)· 2022-06-14
51.1
best: 63.3 (SERE (ViT-B/16, 100ep, 224x224, SSL+FT))
RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks arXiv:2206.06637
10-shot image generationonImageNet-S
mIoU (val)· 2022-06-14
51.3
best: 63.2 (TEC (ViT-B/16, 224x224, SSL+FT, mmseg))
RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks arXiv:2206.06637