SliceNet

Reported on 5 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.

Computer Vision2 results

Depth EstimationonStanford2D3D Panoramic
RMSE
0.3684
best: 0.2619 (HiMODE)
Depth EstimationonStanford2D3D Panoramic
absolute relative error
0.0744
best: 0.0405 (PanoFormer)

Methodology2 results

3DonStanford2D3D Panoramic
RMSE
0.3684
best: 0.2619 (HiMODE)
3DonStanford2D3D Panoramic
absolute relative error
0.0744
best: 0.0405 (PanoFormer)

Natural Language Processing1 result

Machine TranslationonWMT2014 English-German
BLEU score· 2017-06-09
26.1
best: 35.14 (Transformer Cycle (Rev))
Depthwise Separable Convolutions for Neural Machine Translation arXiv:1706.03059