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/M2-Encoder

M2-Encoder

Reported on 13 benchmarks across 2 tasks · 1 paper · 2 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
Text-to-image R@5· uses extra data· 2024-01-29
99.5
SOTA
M2-Encoder: Advancing Bilingual Image-Text Understanding by Large-scale Efficient Pretraining arXiv:2401.15896
Image Retrieval with Multi-Modal QueryonFlickr30k
Image-to-text R@1· uses extra data· 2024-01-29
91.2
best: 98.8 (X2-VLM (large))
M2-Encoder: Advancing Bilingual Image-Text Understanding by Large-scale Efficient Pretraining arXiv:2401.15896
Image Retrieval with Multi-Modal QueryonFlickr30k
Image-to-text R@10· uses extra data· 2024-01-29
99.6
best: 100 (X2-VLM (large))
M2-Encoder: Advancing Bilingual Image-Text Understanding by Large-scale Efficient Pretraining arXiv:2401.15896
Image Retrieval with Multi-Modal QueryonFlickr30k
Image-to-text R@5· uses extra data· 2024-01-29
99.2
best: 100 (X2-VLM (large))
M2-Encoder: Advancing Bilingual Image-Text Understanding by Large-scale Efficient Pretraining arXiv:2401.15896
Image Retrieval with Multi-Modal QueryonFlickr30k
Text-to-image R@1· uses extra data· 2024-01-29
92.2
best: 93.3 (ERNIE-ViL 2.0)
M2-Encoder: Advancing Bilingual Image-Text Understanding by Large-scale Efficient Pretraining arXiv:2401.15896
Image Retrieval with Multi-Modal QueryonFlickr30k
Text-to-image R@10· uses extra data· 2024-01-29
99.7
best: 99.8 (ERNIE-ViL 2.0)
M2-Encoder: Advancing Bilingual Image-Text Understanding by Large-scale Efficient Pretraining arXiv:2401.15896
Image Retrieval with Multi-Modal QueryonCOCO 2014
Image-to-text R@1· 2024-01-29
72.8
best: 84.8 (BEiT-3)
M2-Encoder: Advancing Bilingual Image-Text Understanding by Large-scale Efficient Pretraining arXiv:2401.15896
Image Retrieval with Multi-Modal QueryonCOCO 2014
Image-to-text R@10· 2024-01-29
96.3
best: 98.5 (X2-VLM (large))
M2-Encoder: Advancing Bilingual Image-Text Understanding by Large-scale Efficient Pretraining arXiv:2401.15896
Image Retrieval with Multi-Modal QueryonCOCO 2014
Image-to-text R@5· 2024-01-29
92.3
best: 96.5 (X2-VLM (large))
M2-Encoder: Advancing Bilingual Image-Text Understanding by Large-scale Efficient Pretraining arXiv:2401.15896
Image Retrieval with Multi-Modal QueryonCOCO 2014
Text-to-image R@1· 2024-01-29
56.5
best: 68 (VAST)
M2-Encoder: Advancing Bilingual Image-Text Understanding by Large-scale Efficient Pretraining arXiv:2401.15896
Image Retrieval with Multi-Modal QueryonCOCO 2014
Text-to-image R@10· 2024-01-29
88.8
best: 92.8 (VAST)
M2-Encoder: Advancing Bilingual Image-Text Understanding by Large-scale Efficient Pretraining arXiv:2401.15896
Image Retrieval with Multi-Modal QueryonCOCO 2014
Text-to-image R@5· 2024-01-29
81.6
best: 92.8 (BEiT-3)
M2-Encoder: Advancing Bilingual Image-Text Understanding by Large-scale Efficient Pretraining arXiv:2401.15896

Computer Vision1 result

Zero-Shot Transfer Image ClassificationonImageNet
Accuracy (Private)· uses extra data· 2024-01-29
88.5
SOTA
M2-Encoder: Advancing Bilingual Image-Text Understanding by Large-scale Efficient Pretraining arXiv:2401.15896