OSCAR

Reported on 5 benchmarks across 4 tasks · 1 paper · 5 SOTA

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

Natural Language Processing3 results

Image Captioningonnocaps-val-overall
CIDEr· 2020-04-13
80.9
best: 121.6 (BLIP-2 ViT-G FlanT5 XL (zero-shot))
SOTA
Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks arXiv:2004.06165
Image Captioningonnocaps-val-overall
SPICE· 2020-04-13
11.3
best: 15.8 (BLIP-2 ViT-G FlanT5 XL (zero-shot))
SOTA
Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks arXiv:2004.06165
Cross-Modal RetrievalonCommercialAdsDataset
ADD(S) AUC· 2020-04-13
87.45
best: 91.73 (AlignCMSS)
SOTA
Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks arXiv:2004.06165

Miscellaneous2 results

Image Retrieval with Multi-Modal QueryonCommercialAdsDataset
ADD(S) AUC· 2020-04-13
87.45
best: 91.73 (AlignCMSS)
SOTA
Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks arXiv:2004.06165
Cross-Modal Information RetrievalonCommercialAdsDataset
ADD(S) AUC· 2020-04-13
87.45
best: 91.73 (AlignCMSS)
SOTA
Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks arXiv:2004.06165