Task
Zero Shot Image Classification
A
kakaobrain/align-base
Zero Shot Image Classification·kakaobrain· 12.3K· 31
The ALIGN model was proposed in "Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision" by Chao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen, Zarana Parekh, Hieu Pham, Quoc V. Le, Yunhsuan Sung, Zhen Li, Tom Duerig. ALIGN features a dual-encoder architecture with EfficientNet as its vision encoder and BERT as its text encoder, and learns to align visual and text repr
# pull & run locally
pip install mlforge-sdk && mlforge pull kakaobrain/align-base
pip install mlforge-sdk && mlforge pull kakaobrain/align-base
Model details
Provider
kakaobrain
Framework
transformers
Size
1.9 GB
Downloads
12.3K
Likes
31
Paper
arXiv:2102.05918
Updated
2023-03-08
About kakaobrain/align-base
The ALIGN model was proposed in "Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision" by Chao Jia, Yinfei Yang, Ye Xia, Yi-Ting Chen, Zarana Parekh, Hieu Pham, Quoc V. Le, Yunhsuan Sung, Zhen Li, Tom Duerig. ALIGN features a dual-encoder architecture with EfficientNet as its vision encoder and BERT as its text encoder, and learns to align visual and text representations with contrastive learning. Unlike previous work, ALIGN leverages a massive noisy dataset and shows that the scale of the corpus can be used to achieve SOTA representations with a simple recipe.