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/CoCa

CoCa

Reported on 29 benchmarks across 8 tasks · 1 paper · 11 SOTA

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

Miscellaneous12 results

Image Retrieval with Multi-Modal QueryonFlickr30k
Image-to-text R@1· 2022-05-04
92.5
best: 98.8 (X2-VLM (large))
CoCa: Contrastive Captioners are Image-Text Foundation Models arXiv:2205.01917
Image Retrieval with Multi-Modal QueryonFlickr30k
Image-to-text R@10· 2022-05-04
99.9
best: 100 (X2-VLM (large))
CoCa: Contrastive Captioners are Image-Text Foundation Models arXiv:2205.01917
Image Retrieval with Multi-Modal QueryonFlickr30k
Image-to-text R@5· 2022-05-04
99.5
best: 100 (X2-VLM (large))
CoCa: Contrastive Captioners are Image-Text Foundation Models arXiv:2205.01917
Image Retrieval with Multi-Modal QueryonFlickr30k
Text-to-image R@1· 2022-05-04
80.4
best: 93.3 (ERNIE-ViL 2.0)
CoCa: Contrastive Captioners are Image-Text Foundation Models arXiv:2205.01917
Image Retrieval with Multi-Modal QueryonFlickr30k
Text-to-image R@10· 2022-05-04
97.7
best: 99.8 (ERNIE-ViL 2.0)
CoCa: Contrastive Captioners are Image-Text Foundation Models arXiv:2205.01917
Image Retrieval with Multi-Modal QueryonFlickr30k
Text-to-image R@5· 2022-05-04
95.7
best: 99.5 (M2-Encoder)
CoCa: Contrastive Captioners are Image-Text Foundation Models arXiv:2205.01917
Image Retrieval with Multi-Modal QueryonCOCO 2014
Image-to-text R@1· 2022-05-04
66.3
best: 84.8 (BEiT-3)
CoCa: Contrastive Captioners are Image-Text Foundation Models arXiv:2205.01917
Image Retrieval with Multi-Modal QueryonCOCO 2014
Image-to-text R@10· 2022-05-04
91.8
best: 98.5 (X2-VLM (large))
CoCa: Contrastive Captioners are Image-Text Foundation Models arXiv:2205.01917
Image Retrieval with Multi-Modal QueryonCOCO 2014
Image-to-text R@5· 2022-05-04
86.2
best: 96.5 (X2-VLM (large))
CoCa: Contrastive Captioners are Image-Text Foundation Models arXiv:2205.01917
Image Retrieval with Multi-Modal QueryonCOCO 2014
Text-to-image R@1· 2022-05-04
51.2
best: 68 (VAST)
CoCa: Contrastive Captioners are Image-Text Foundation Models arXiv:2205.01917
Image Retrieval with Multi-Modal QueryonCOCO 2014
Text-to-image R@10· 2022-05-04
82
best: 92.8 (VAST)
CoCa: Contrastive Captioners are Image-Text Foundation Models arXiv:2205.01917
Image Retrieval with Multi-Modal QueryonCOCO 2014
Text-to-image R@5· 2022-05-04
74.2
best: 92.8 (BEiT-3)
CoCa: Contrastive Captioners are Image-Text Foundation Models arXiv:2205.01917

Natural Language Processing8 results

Image CaptioningonCOCO Captions
METEOR· 2022-05-04
33.9
SOTA
CoCa: Contrastive Captioners are Image-Text Foundation Models arXiv:2205.01917
Visual Question AnsweringonVQA v2 test-dev
Accuracy· 2022-05-04
82.3
SOTA
CoCa: Contrastive Captioners are Image-Text Foundation Models arXiv:2205.01917
Visual Question Answering (VQA)onVQA v2 test-dev
Accuracy· 2022-05-04
82.3
best: 84.3 (PaLI)
CoCa: Contrastive Captioners are Image-Text Foundation Models arXiv:2205.01917
Natural Language InferenceonSNLI-VE val
Accuracy· 2022-05-04
87
best: 91 (OFA)
CoCa: Contrastive Captioners are Image-Text Foundation Models arXiv:2205.01917
Natural Language InferenceonSNLI-VE test
Accuracy· 2022-05-04
87.1
best: 91.2 (OFA)
CoCa: Contrastive Captioners are Image-Text Foundation Models arXiv:2205.01917
Image CaptioningonCOCO Captions
BLEU-4· 2022-05-04
40.9
best: 46.5 (mPLUG)
CoCa: Contrastive Captioners are Image-Text Foundation Models arXiv:2205.01917
Image CaptioningonCOCO Captions
CIDER· 2022-05-04
143.6
best: 155.1 (mPLUG)
CoCa: Contrastive Captioners are Image-Text Foundation Models arXiv:2205.01917
Image CaptioningonCOCO Captions
SPICE· 2022-05-04
24.7
best: 27 (VAST)
CoCa: Contrastive Captioners are Image-Text Foundation Models arXiv:2205.01917

Computer Vision7 results

Image ClassificationonObjectNet
Top-1 Accuracy· uses extra data· 2022-05-04
82.7
SOTA
CoCa: Contrastive Captioners are Image-Text Foundation Models arXiv:2205.01917
Zero-Shot Transfer Image ClassificationonImageNet V2
Accuracy (Private)· 2022-05-04
80.7
best: 81.2 (BASIC (Lion))
SOTA
CoCa: Contrastive Captioners are Image-Text Foundation Models arXiv:2205.01917
Zero-Shot Transfer Image ClassificationonImageNet-A
Accuracy (Private)· 2022-05-04
90.2
SOTA
CoCa: Contrastive Captioners are Image-Text Foundation Models arXiv:2205.01917
Zero-Shot Transfer Image ClassificationonImageNet
Accuracy (Private)· uses extra data· 2022-05-04
86.3
best: 88.5 (M2-Encoder)
SOTA
CoCa: Contrastive Captioners are Image-Text Foundation Models arXiv:2205.01917
Zero-Shot Transfer Image ClassificationonImageNet-R
Accuracy· 2022-05-04
96.5
best: 96.8 (BASIC (Lion))
SOTA
CoCa: Contrastive Captioners are Image-Text Foundation Models arXiv:2205.01917
Zero-Shot Transfer Image ClassificationonObjectNet
Accuracy (Private)· 2022-05-04
82.7
best: 87.6 (LiT-22B)
SOTA
CoCa: Contrastive Captioners are Image-Text Foundation Models arXiv:2205.01917
Zero-Shot Transfer Image ClassificationonImageNet-Sketch
Accuracy (Private)· 2022-05-04
77.6
SOTA
CoCa: Contrastive Captioners are Image-Text Foundation Models arXiv:2205.01917

Reasoning2 results

Visual ReasoningonNLVR2 Dev
Accuracy· 2022-05-04
86.1
best: 91.51 (BEiT-3)
SOTA
CoCa: Contrastive Captioners are Image-Text Foundation Models arXiv:2205.01917
Visual ReasoningonNLVR2 Test
Accuracy· 2022-05-04
87
best: 92.58 (BEiT-3)
SOTA
CoCa: Contrastive Captioners are Image-Text Foundation Models arXiv:2205.01917