DiCENet

Reported on 3 benchmarks across 3 tasks · 1 paper

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

Medical1 result

Semantic SegmentationonCityscapes val
mIoU· 2019-06-08
63.4
best: 90.3 (EfficientPS (Cityscapes-fine))
DiCENet: Dimension-wise Convolutions for Efficient Networks arXiv:1906.03516

Computer Vision1 result

Image ClassificationonImageNet
GFLOPs· 2019-06-08
0.553
best: 1478 (InternImage-H)
DiCENet: Dimension-wise Convolutions for Efficient Networks arXiv:1906.03516

Audio1 result

10-shot image generationonCityscapes val
mIoU· 2019-06-08
63.4
best: 90.3 (EfficientPS (Cityscapes-fine))
DiCENet: Dimension-wise Convolutions for Efficient Networks arXiv:1906.03516