0
Learning Transferable Visual Models From Natural Language Supervision
Alec Radford, Jong Wook Kim, Chris Hallacy et al., 2021. Proceedings of ICML 2021.
Introduces CLIP, a model that learns to match images with text by training on a large collection of image-caption pairs.
What it's used for here
The surveys propose CLIP-style embeddings for clustering glyphs and as an alternative to hand-coding the herbal drawings when matching text to images.
Cited by on this site 2 records
2 methods surveys
SRCMathematics, inductive methods
Cite it
Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., & Sutskever, I. (2021). Learning Transferable Visual Models From Natural Language Supervision. Proceedings of ICML 2021. https://arxiv.org/abs/2103.00020
@article{radford2021learning,
author = {Radford, Alec and Kim, Jong Wook and Hallacy, Chris and Ramesh, Aditya and Goh, Gabriel and Agarwal, Sandhini and Sastry, Girish and Askell, Amanda and Mishkin, Pamela and Clark, Jack and Krueger, Gretchen and Sutskever, Ilya},
title = {Learning Transferable Visual Models From Natural Language Supervision},
journal = {Proceedings of ICML 2021},
year = {2021},
url = {https://arxiv.org/abs/2103.00020}
}TY - JOUR TI - Learning Transferable Visual Models From Natural Language Supervision AU - Radford, Alec AU - Kim, Jong Wook AU - Hallacy, Chris AU - Ramesh, Aditya AU - Goh, Gabriel AU - Agarwal, Sandhini AU - Sastry, Girish AU - Askell, Amanda AU - Mishkin, Pamela AU - Clark, Jack AU - Krueger, Gretchen AU - Sutskever, Ilya PY - 2021 JO - Proceedings of ICML 2021 UR - https://arxiv.org/abs/2103.00020 ER -
Radford, Alec et al.. “Learning Transferable Visual Models From Natural Language Supervision.” Proceedings of ICML 2021 (2021).