ERNIE-ViL2.0

Reported on 6 benchmarks across 2 tasks · 1 paper · 5 SOTA

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

Computer Vision3 results

Image RetrievalonAIC-ICC
Recall@1· 2022-09-30
19
SOTA
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Image RetrievalonAIC-ICC
Recall@10· 2022-09-30
43.5
SOTA
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Image RetrievalonAIC-ICC
Recall@5· 2022-09-30
35.3
best: 39.1 (CMCL)
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270

Natural Language Processing3 results

Image-to-Text RetrievalonAIC-ICC
Recall@1· 2022-09-30
33.7
SOTA
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Image-to-Text RetrievalonAIC-ICC
Recall@10· 2022-09-30
60
SOTA
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Image-to-Text RetrievalonAIC-ICC
Recall@5· 2022-09-30
52.1
SOTA
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270