Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/Airbert

Airbert

Reported on 11 benchmarks across 2 tasks · 1 paper · 2 SOTA

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

Computer Vision6 results

Object LocalizationonREVERIE
Nav-Length
17.91
best: 48.61 (SIA)
Object LocalizationonREVERIE
Nav-OSucc
34.2
best: 57.12 (OSMaN)
Object LocalizationonREVERIE
Nav-SPL
23.61
best: 47.78 (OSMaN)
Object LocalizationonREVERIE
Nav-Succ
30.28
best: 54.39 (SUSA)
Object LocalizationonREVERIE
RGS
16.83
best: 36.11 (SUSA)
Object LocalizationonREVERIE
RGSPL
13.28
best: 32.99 (OSMaN)

Robots5 results

Vision and Language NavigationonVLN Challenge
error· 2021-08-20
2.58
best: 1.61 (human)
SOTA
Airbert: In-domain Pretraining for Vision-and-Language Navigation arXiv:2108.09105
Vision and Language NavigationonVLN Challenge
success· 2021-08-20
0.78
best: 0.86 (human)
SOTA
Airbert: In-domain Pretraining for Vision-and-Language Navigation arXiv:2108.09105
Vision and Language NavigationonVLN Challenge
length· 2021-08-20
686.54
best: 1257.38 (Speaker-Follower)
Airbert: In-domain Pretraining for Vision-and-Language Navigation arXiv:2108.09105
Vision and Language NavigationonVLN Challenge
oracle success· 2021-08-20
0.99
best: 1 (FOAM-Beam Search)
Airbert: In-domain Pretraining for Vision-and-Language Navigation arXiv:2108.09105
Vision and Language NavigationonVLN Challenge
spl· 2021-08-20
0.01
best: 0.76 (human)
Airbert: In-domain Pretraining for Vision-and-Language Navigation arXiv:2108.09105