leduckhai/ViT5-VietMedSum
Summarization
β’
Updated
β’
112
Le Duc Khai
leduckhai
AI & ML interests
None yet
Recent Activity
new activity
9 days ago
leduckhai/MultiMed:Transcription langauge is different from audio language
updated
a model
3 months ago
leduckhai/ViT5-VietMedSum
updated
a dataset
3 months ago
leduckhai/VietMed-Sum
Organizations
leduckhai's activity
Transcription langauge is different from audio language
3
#3 opened 15 days ago
by
Shamus
updated
a
model
3 months ago
updated
a
dataset
3 months ago
updated
a
dataset
5 months ago
authored
2
papers
7 months ago
[bot] Conversion to Parquet
#1 opened 7 months ago
by
parquet-converter
authored
2
papers
7 months ago
upvoted
a
paper
7 months ago
updated
a
dataset
8 months ago
reacted to
merve's
post with π₯
8 months ago
Post
4352
Florence-2 is a new vision foundation model capable of a wide variety of tasks π€―
Demo ππ» gokaygokay/Florence-2
Collection ππ» microsoft/florence-6669f44df0d87d9c3bfb76de
This model can handle tasks that vary from OCR to semantic segmentation.
The difference from previous models is that the authors have compiled a dataset consisting of 126M images with 5.4B annotations labelled with their own data engine pseudolabelled by smaller specialized models and APIs.
The model has a similar architecture to previous models: an image encoder and a multimodality encoder with a text decoder. The authors have compiled the multitask dataset with prompts for each task.
You can also fine-tune this model on any task of choice. The authors also released different results on downstream tasks and reported their results when un/freezing the vision encoder π€π
They have released fine-tuned models too, you can find them in the collection above π€
Demo ππ» gokaygokay/Florence-2
Collection ππ» microsoft/florence-6669f44df0d87d9c3bfb76de
This model can handle tasks that vary from OCR to semantic segmentation.
The difference from previous models is that the authors have compiled a dataset consisting of 126M images with 5.4B annotations labelled with their own data engine pseudolabelled by smaller specialized models and APIs.
The model has a similar architecture to previous models: an image encoder and a multimodality encoder with a text decoder. The authors have compiled the multitask dataset with prompts for each task.
You can also fine-tune this model on any task of choice. The authors also released different results on downstream tasks and reported their results when un/freezing the vision encoder π€π
They have released fine-tuned models too, you can find them in the collection above π€
- 3 replies
authored
a
paper
9 months ago
liked
a
dataset
9 months ago
updated
a
dataset
9 months ago
upvoted
a
paper
10 months ago