Edits from Tristan
Browse files
README.md
CHANGED
|
@@ -10,7 +10,7 @@ library_name: open_clip
|
|
| 10 |
|
| 11 |
# BiomedCLIP-PubMedBERT_256-vit_base_patch16_224
|
| 12 |
|
| 13 |
-
[BiomedCLIP](https://aka.ms/biomedclip-paper) is a biomedical vision-language foundation model that is pretrained on [PMC-15M](https://aka.ms/biomedclip-paper) dataset using contrastive learning.
|
| 14 |
It uses PubMedBERT as the text encoder and Vision Transformer as the image encoder, with domain-specific adaptations.
|
| 15 |
It can perform various vision-language processing (VLP) tasks such as cross-modal retrieval, image classification, and visual question answering.
|
| 16 |
BiomedCLIP establishes new state of the art in a wide range of standard datasets, and substantially outperforms prior VLP approaches:
|
|
|
|
| 10 |
|
| 11 |
# BiomedCLIP-PubMedBERT_256-vit_base_patch16_224
|
| 12 |
|
| 13 |
+
[BiomedCLIP](https://aka.ms/biomedclip-paper) is a biomedical vision-language foundation model that is pretrained on [PMC-15M](https://aka.ms/biomedclip-paper), a dataset of 15 million figure-caption pairs extracted from biomedical research articles in PubMed Central, using contrastive learning.
|
| 14 |
It uses PubMedBERT as the text encoder and Vision Transformer as the image encoder, with domain-specific adaptations.
|
| 15 |
It can perform various vision-language processing (VLP) tasks such as cross-modal retrieval, image classification, and visual question answering.
|
| 16 |
BiomedCLIP establishes new state of the art in a wide range of standard datasets, and substantially outperforms prior VLP approaches:
|