Hugging Face's logo

wisdomik
/
QuiltNet-B-16-PMB

Zero-Shot Image Classification
OpenCLIP
clip
vision
language
histopathology
histology
medical
Model card Files
xet
 Community
1
wisdomik commited on
Commit
fc97dde
·
1 Parent(s): d173fa8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -27,7 +27,7 @@ pipeline_tag: zero-shot-image-classification
27
 
28
 
29
  ## QuiltNet-B-16-PMB Description
30
- QuiltNet-B-32/PMB is a ViT-B/16 image tower and PubMedBERT text tower vision-language foundation model trained on the [Quilt-1M](https://quilt1m.github.io/) dataset curated from representative histopathology videos.
31
  It can perform various vision-language processing (VLP) tasks such as cross-modal retrieval, image classification, and visual question answering.
32
  QuiltNet establishes new state of the art in a wide range of standard datasets, and substantially outperforms prior VLP approaches:
33
 
 
27
 
28
 
29
  ## QuiltNet-B-16-PMB Description
30
+ [QuiltNet-B-32/PMB](https://github.com/wisdomikezogwo/quilt1m/) is a ViT-B/16 image tower and PubMedBERT text tower vision-language foundation model trained on the [Quilt-1M](https://quilt1m.github.io/) dataset curated from representative histopathology videos.
31
  It can perform various vision-language processing (VLP) tasks such as cross-modal retrieval, image classification, and visual question answering.
32
  QuiltNet establishes new state of the art in a wide range of standard datasets, and substantially outperforms prior VLP approaches:
33