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/ERNIE-ViL 2.0

ERNIE-ViL 2.0

Reported on 39 benchmarks across 4 tasks · 1 paper · 11 SOTA

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

Miscellaneous36 results

Image Retrieval with Multi-Modal QueryonFlickr30k
Text-to-image R@1· uses extra data· 2022-09-30
93.3
SOTA
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Image Retrieval with Multi-Modal QueryonFlickr30k
Text-to-image R@10· uses extra data· 2022-09-30
99.8
SOTA
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Image Retrieval with Multi-Modal QueryonFlickr30k
Text-to-image R@5· uses extra data· 2022-09-30
99.4
best: 99.5 (M2-Encoder)
SOTA
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Cross-Modal Information RetrievalonFlickr30k
Text-to-image R@1· uses extra data· 2022-09-30
93.3
SOTA
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Cross-Modal Information RetrievalonFlickr30k
Text-to-image R@10· uses extra data· 2022-09-30
99.8
SOTA
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Cross-Modal Information RetrievalonFlickr30k
Text-to-image R@5· uses extra data· 2022-09-30
99.4
SOTA
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Image Retrieval with Multi-Modal QueryonFlickr30k
Image-to-text R@1· uses extra data· 2022-09-30
97.2
best: 98.8 (X2-VLM (large))
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Image Retrieval with Multi-Modal QueryonFlickr30k
Image-to-text R@10· uses extra data· 2022-09-30
100
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Image Retrieval with Multi-Modal QueryonFlickr30k
Image-to-text R@5· uses extra data· 2022-09-30
100
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Image Retrieval with Multi-Modal QueryonCOCO 2014
Image-to-text R@1· uses extra data· 2022-09-30
77.4
best: 84.8 (BEiT-3)
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Image Retrieval with Multi-Modal QueryonCOCO 2014
Image-to-text R@10· uses extra data· 2022-09-30
97.1
best: 98.5 (X2-VLM (large))
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Image Retrieval with Multi-Modal QueryonCOCO 2014
Image-to-text R@5· uses extra data· 2022-09-30
93.6
best: 96.5 (X2-VLM (large))
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Image Retrieval with Multi-Modal QueryonCOCO 2014
Text-to-image R@1· uses extra data· 2022-09-30
59.5
best: 68 (VAST)
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Image Retrieval with Multi-Modal QueryonCOCO 2014
Text-to-image R@10· uses extra data· 2022-09-30
90.1
best: 92.8 (VAST)
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Image Retrieval with Multi-Modal QueryonCOCO 2014
Text-to-image R@5· uses extra data· 2022-09-30
83.4
best: 92.8 (BEiT-3)
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Image Retrieval with Multi-Modal QueryonFlickr30k
Image-to-text R@1· 2022-09-30
91.2
best: 98.8 (X2-VLM (large))
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Image Retrieval with Multi-Modal QueryonFlickr30k
Image-to-text R@10· 2022-09-30
99.8
best: 100 (X2-VLM (large))
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Image Retrieval with Multi-Modal QueryonFlickr30k
Image-to-text R@5· 2022-09-30
99.1
best: 100 (X2-VLM (large))
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Image Retrieval with Multi-Modal QueryonFlickr30k
Text-to-image R@1· 2022-09-30
77.4
best: 93.3
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Image Retrieval with Multi-Modal QueryonFlickr30k
Text-to-image R@10· 2022-09-30
96.4
best: 99.8
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Image Retrieval with Multi-Modal QueryonFlickr30k
Text-to-image R@5· 2022-09-30
93.8
best: 99.5 (M2-Encoder)
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Image Retrieval with Multi-Modal QueryonCOCO 2014
Image-to-text R@1· 2022-09-30
63.1
best: 84.8 (BEiT-3)
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Image Retrieval with Multi-Modal QueryonCOCO 2014
Image-to-text R@10· 2022-09-30
91.4
best: 98.5 (X2-VLM (large))
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Image Retrieval with Multi-Modal QueryonCOCO 2014
Image-to-text R@5· 2022-09-30
85.7
best: 96.5 (X2-VLM (large))
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Image Retrieval with Multi-Modal QueryonCOCO 2014
Text-to-image R@1· 2022-09-30
46
best: 68 (VAST)
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Image Retrieval with Multi-Modal QueryonCOCO 2014
Text-to-image R@10· 2022-09-30
80.4
best: 92.8 (VAST)
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Image Retrieval with Multi-Modal QueryonCOCO 2014
Text-to-image R@5· 2022-09-30
71.4
best: 92.8 (BEiT-3)
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Cross-Modal Information RetrievalonFlickr30k
Image-to-text R@1· uses extra data· 2022-09-30
97.2
best: 98.8 (X2-VLM (large))
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Cross-Modal Information RetrievalonFlickr30k
Image-to-text R@10· uses extra data· 2022-09-30
100
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Cross-Modal Information RetrievalonFlickr30k
Image-to-text R@5· uses extra data· 2022-09-30
100
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Cross-Modal Information RetrievalonCOCO 2014
Image-to-text R@1· uses extra data· 2022-09-30
77.4
best: 84.8 (BEiT-3)
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Cross-Modal Information RetrievalonCOCO 2014
Image-to-text R@10· uses extra data· 2022-09-30
97.1
best: 98.5 (X2-VLM (large))
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Cross-Modal Information RetrievalonCOCO 2014
Image-to-text R@5· uses extra data· 2022-09-30
93.6
best: 96.5 (X2-VLM (large))
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Cross-Modal Information RetrievalonCOCO 2014
Text-to-image R@1· uses extra data· 2022-09-30
59.5
best: 68 (VAST)
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Cross-Modal Information RetrievalonCOCO 2014
Text-to-image R@10· uses extra data· 2022-09-30
90.1
best: 92.8 (VAST)
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Cross-Modal Information RetrievalonCOCO 2014
Text-to-image R@5· uses extra data· 2022-09-30
83.4
best: 92.8 (BEiT-3)
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270

Natural Language Processing15 results

Cross-Modal RetrievalonFlickr30k
Text-to-image R@1· uses extra data· 2022-09-30
93.3
SOTA
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Cross-Modal RetrievalonFlickr30k
Text-to-image R@10· uses extra data· 2022-09-30
99.8
SOTA
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Cross-Modal RetrievalonFlickr30k
Text-to-image R@5· uses extra data· 2022-09-30
99.4
SOTA
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Image-to-Text RetrievalonFlickr30k
Recall@1· 2022-09-30
96.1
best: 97.9 (InternVL-G-FT (finetuned, w/o ranking))
SOTA
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Image-to-Text RetrievalonFlickr30k
Recall@5· 2022-09-30
99.9
best: 100 (InternVL-G-FT (finetuned, w/o ranking))
SOTA
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Cross-Modal RetrievalonFlickr30k
Image-to-text R@1· uses extra data· 2022-09-30
97.2
best: 98.8 (X2-VLM (large))
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Cross-Modal RetrievalonFlickr30k
Image-to-text R@10· uses extra data· 2022-09-30
100
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Cross-Modal RetrievalonFlickr30k
Image-to-text R@5· uses extra data· 2022-09-30
100
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Cross-Modal RetrievalonCOCO 2014
Image-to-text R@1· uses extra data· 2022-09-30
77.4
best: 84.8 (BEiT-3)
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Cross-Modal RetrievalonCOCO 2014
Image-to-text R@10· uses extra data· 2022-09-30
97.1
best: 98.5 (X2-VLM (large))
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Cross-Modal RetrievalonCOCO 2014
Image-to-text R@5· uses extra data· 2022-09-30
93.6
best: 96.5 (X2-VLM (large))
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Cross-Modal RetrievalonCOCO 2014
Text-to-image R@1· uses extra data· 2022-09-30
59.5
best: 68 (VAST)
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Cross-Modal RetrievalonCOCO 2014
Text-to-image R@10· uses extra data· 2022-09-30
90.1
best: 92.8 (VAST)
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Cross-Modal RetrievalonCOCO 2014
Text-to-image R@5· uses extra data· 2022-09-30
83.4
best: 92.8 (BEiT-3)
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270
Image-to-Text RetrievalonFlickr30k
Recall@10· 2022-09-30
100
ERNIE-ViL 2.0: Multi-view Contrastive Learning for Image-Text Pre-training arXiv:2209.15270