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/ALIGN

ALIGN

Reported on 43 benchmarks across 6 tasks · 2 papers · 37 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
Image-to-text R@1· uses extra data· 2021-02-11
95.3
best: 98.8 (X2-VLM (large))
SOTA
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Image Retrieval with Multi-Modal QueryonFlickr30k
Image-to-text R@10· uses extra data· 2021-02-11
100
SOTA
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Image Retrieval with Multi-Modal QueryonFlickr30k
Image-to-text R@5· uses extra data· 2021-02-11
99.8
best: 100 (X2-VLM (large))
SOTA
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Image Retrieval with Multi-Modal QueryonFlickr30k
Text-to-image R@1· uses extra data· 2021-02-11
84.9
best: 93.3 (ERNIE-ViL 2.0)
SOTA
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Image Retrieval with Multi-Modal QueryonFlickr30k
Text-to-image R@10· uses extra data· 2021-02-11
98.6
best: 99.8 (ERNIE-ViL 2.0)
SOTA
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Image Retrieval with Multi-Modal QueryonFlickr30k
Text-to-image R@5· uses extra data· 2021-02-11
97.4
best: 99.5 (M2-Encoder)
SOTA
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Image Retrieval with Multi-Modal QueryonCOCO 2014
Image-to-text R@1· uses extra data· 2021-02-11
77
best: 84.8 (BEiT-3)
SOTA
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Image Retrieval with Multi-Modal QueryonCOCO 2014
Image-to-text R@10· uses extra data· 2021-02-11
96.9
best: 98.5 (X2-VLM (large))
SOTA
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Image Retrieval with Multi-Modal QueryonCOCO 2014
Image-to-text R@5· uses extra data· 2021-02-11
93.5
best: 96.5 (X2-VLM (large))
SOTA
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Image Retrieval with Multi-Modal QueryonCOCO 2014
Text-to-image R@1· uses extra data· 2021-02-11
59.9
best: 68 (VAST)
SOTA
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Image Retrieval with Multi-Modal QueryonCOCO 2014
Text-to-image R@5· uses extra data· 2021-02-11
83.3
best: 92.8 (BEiT-3)
SOTA
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Cross-Modal Information RetrievalonFlickr30k
Image-to-text R@1· uses extra data· 2021-02-11
95.3
best: 98.8 (X2-VLM (large))
SOTA
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Cross-Modal Information RetrievalonFlickr30k
Image-to-text R@10· uses extra data· 2021-02-11
100
SOTA
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Cross-Modal Information RetrievalonFlickr30k
Image-to-text R@5· uses extra data· 2021-02-11
99.8
best: 100 (X2-VLM (large))
SOTA
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Cross-Modal Information RetrievalonFlickr30k
Text-to-image R@1· uses extra data· 2021-02-11
84.9
best: 93.3 (ERNIE-ViL 2.0)
SOTA
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Cross-Modal Information RetrievalonFlickr30k
Text-to-image R@10· uses extra data· 2021-02-11
98.6
best: 99.8 (ERNIE-ViL 2.0)
SOTA
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Cross-Modal Information RetrievalonFlickr30k
Text-to-image R@5· uses extra data· 2021-02-11
97.4
best: 99.4 (ERNIE-ViL 2.0)
SOTA
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Cross-Modal Information RetrievalonCOCO 2014
Image-to-text R@1· uses extra data· 2021-02-11
77
best: 84.8 (BEiT-3)
SOTA
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Cross-Modal Information RetrievalonCOCO 2014
Image-to-text R@10· uses extra data· 2021-02-11
96.9
best: 98.5 (X2-VLM (large))
SOTA
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Cross-Modal Information RetrievalonCOCO 2014
Image-to-text R@5· uses extra data· 2021-02-11
93.5
best: 96.5 (X2-VLM (large))
SOTA
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Cross-Modal Information RetrievalonCOCO 2014
Text-to-image R@1· uses extra data· 2021-02-11
59.9
best: 68 (VAST)
SOTA
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Cross-Modal Information RetrievalonCOCO 2014
Text-to-image R@5· uses extra data· 2021-02-11
83.3
best: 92.8 (BEiT-3)
SOTA
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Image Retrieval with Multi-Modal QueryonCOCO 2014
Text-to-image R@10· uses extra data· 2021-02-11
89.8
best: 92.8 (VAST)
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Image Retrieval with Multi-Modal QueryonFlickr30k
Image-to-text R@1· 2021-02-11
88.6
best: 98.8 (X2-VLM (large))
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Image Retrieval with Multi-Modal QueryonFlickr30k
Image-to-text R@10· 2021-02-11
99.7
best: 100 (X2-VLM (large))
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Image Retrieval with Multi-Modal QueryonFlickr30k
Image-to-text R@5· 2021-02-11
98.7
best: 100 (X2-VLM (large))
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Image Retrieval with Multi-Modal QueryonFlickr30k
Text-to-image R@1· 2021-02-11
75.7
best: 93.3 (ERNIE-ViL 2.0)
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Image Retrieval with Multi-Modal QueryonFlickr30k
Text-to-image R@10· 2021-02-11
96.8
best: 99.8 (ERNIE-ViL 2.0)
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Image Retrieval with Multi-Modal QueryonFlickr30k
Text-to-image R@5· 2021-02-11
93.8
best: 99.5 (M2-Encoder)
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Image Retrieval with Multi-Modal QueryonCOCO 2014
Image-to-text R@1· 2021-02-11
58.6
best: 84.8 (BEiT-3)
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Image Retrieval with Multi-Modal QueryonCOCO 2014
Image-to-text R@10· 2021-02-11
89.7
best: 98.5 (X2-VLM (large))
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Image Retrieval with Multi-Modal QueryonCOCO 2014
Image-to-text R@5· 2021-02-11
83
best: 96.5 (X2-VLM (large))
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Image Retrieval with Multi-Modal QueryonCOCO 2014
Text-to-image R@1· 2021-02-11
45.6
best: 68 (VAST)
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Image Retrieval with Multi-Modal QueryonCOCO 2014
Text-to-image R@10· 2021-02-11
78.6
best: 92.8 (VAST)
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Image Retrieval with Multi-Modal QueryonCOCO 2014
Text-to-image R@5· 2021-02-11
69.8
best: 92.8 (BEiT-3)
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Cross-Modal Information RetrievalonCOCO 2014
Text-to-image R@10· uses extra data· 2021-02-11
89.8
best: 92.8 (VAST)
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918

Natural Language Processing12 results

Cross-Modal RetrievalonFlickr30k
Image-to-text R@1· uses extra data· 2021-02-11
95.3
best: 98.8 (X2-VLM (large))
SOTA
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Cross-Modal RetrievalonFlickr30k
Image-to-text R@10· uses extra data· 2021-02-11
100
SOTA
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Cross-Modal RetrievalonFlickr30k
Image-to-text R@5· uses extra data· 2021-02-11
99.8
best: 100 (X2-VLM (large))
SOTA
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Cross-Modal RetrievalonFlickr30k
Text-to-image R@1· uses extra data· 2021-02-11
84.9
best: 93.3 (ERNIE-ViL 2.0)
SOTA
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Cross-Modal RetrievalonFlickr30k
Text-to-image R@10· uses extra data· 2021-02-11
98.6
best: 99.8 (ERNIE-ViL 2.0)
SOTA
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Cross-Modal RetrievalonFlickr30k
Text-to-image R@5· uses extra data· 2021-02-11
97.4
best: 99.4 (ERNIE-ViL 2.0)
SOTA
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Cross-Modal RetrievalonCOCO 2014
Image-to-text R@1· uses extra data· 2021-02-11
77
best: 84.8 (BEiT-3)
SOTA
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Cross-Modal RetrievalonCOCO 2014
Image-to-text R@10· uses extra data· 2021-02-11
96.9
best: 98.5 (X2-VLM (large))
SOTA
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Cross-Modal RetrievalonCOCO 2014
Image-to-text R@5· uses extra data· 2021-02-11
93.5
best: 96.5 (X2-VLM (large))
SOTA
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Cross-Modal RetrievalonCOCO 2014
Text-to-image R@1· uses extra data· 2021-02-11
59.9
best: 68 (VAST)
SOTA
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Cross-Modal RetrievalonCOCO 2014
Text-to-image R@5· uses extra data· 2021-02-11
83.3
best: 92.8 (BEiT-3)
SOTA
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Cross-Modal RetrievalonCOCO 2014
Text-to-image R@10· uses extra data· 2021-02-11
89.8
best: 92.8 (VAST)
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918

Computer Vision7 results

Zero-Shot Transfer Image ClassificationonImageNet V2
Accuracy (Private)· 2021-02-11
70.1
best: 81.2 (BASIC (Lion))
SOTA
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Zero-Shot Transfer Image ClassificationonImageNet-A
Accuracy (Private)· 2021-02-11
75.8
best: 90.2 (CoCa)
SOTA
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Zero-Shot Transfer Image ClassificationonImageNet
Accuracy (Private)· 2021-02-11
76.4
best: 88.5 (M2-Encoder)
SOTA
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Zero-Shot Transfer Image ClassificationonImageNet-R
Accuracy· 2021-02-11
92.2
best: 96.8 (BASIC (Lion))
SOTA
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Image ClassificationonObjectNet
Top-1 Accuracy· uses extra data· 2021-11-19
72.2
best: 82.7 (CoCa)
Combined Scaling for Zero-shot Transfer Learning arXiv:2111.10050
Image ClassificationonFood-101
Accuracy· uses extra data· 2021-02-11
95.88
best: 98.6 (CAP)
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918
Fine-Grained Image ClassificationonFood-101
Accuracy· uses extra data· 2021-02-11
95.88
best: 98.6 (CAP)
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision arXiv:2102.05918