FusionNet

Reported on 6 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.

Natural Language Processing2 results

Question AnsweringonSQuAD1.1 dev
EM· 2017-11-16
75.3
best: 90.06 (T5-11B)
FusionNet: Fusing via Fully-Aware Attention with Application to Machine Comprehension arXiv:1711.07341
Question AnsweringonSQuAD1.1 dev
F1· 2017-11-16
83.6
best: 95.77 (XLNet+DSC)
FusionNet: Fusing via Fully-Aware Attention with Application to Machine Comprehension arXiv:1711.07341

Medical2 results

Semantic SegmentationonS3DIS Area5
mAcc
72.3
best: 81.6 (Sonata + PTv3)
Semantic SegmentationonS3DIS Area5
mIoU
67.2
best: 76 (Sonata + PTv3)

Audio2 results

10-shot image generationonS3DIS Area5
mAcc
72.3
best: 81.6 (Sonata + PTv3)
10-shot image generationonS3DIS Area5
mIoU
67.2
best: 76 (Sonata + PTv3)