Self-Supervised Auxiliary Reasoning Tasks (Beam Search)

Reported on 5 benchmarks across 1 task · 1 paper · 2 SOTA

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

Robots5 results

Vision and Language NavigationonVLN Challenge
error· 2019-11-18
3.24
best: 1.61 (human)
SOTA
Vision-Language Navigation with Self-Supervised Auxiliary Reasoning Tasks arXiv:1911.07883
Vision and Language NavigationonVLN Challenge
success· 2019-11-18
0.71
best: 0.86 (human)
SOTA
Vision-Language Navigation with Self-Supervised Auxiliary Reasoning Tasks arXiv:1911.07883
Vision and Language NavigationonVLN Challenge
length· 2019-11-18
40.85
best: 1257.38 (Speaker-Follower)
Vision-Language Navigation with Self-Supervised Auxiliary Reasoning Tasks arXiv:1911.07883
Vision and Language NavigationonVLN Challenge
oracle success· 2019-11-18
0.81
best: 1 (FOAM-Beam Search)
Vision-Language Navigation with Self-Supervised Auxiliary Reasoning Tasks arXiv:1911.07883
Vision and Language NavigationonVLN Challenge
spl· 2019-11-18
0.21
best: 0.76 (human)
Vision-Language Navigation with Self-Supervised Auxiliary Reasoning Tasks arXiv:1911.07883