OpenFace-CQUPT
commited on
Commit
•
b92bc50
1
Parent(s):
d483e35
Update README.md
Browse files
README.md
CHANGED
@@ -8,7 +8,18 @@ language:
|
|
8 |
|
9 |
We developed a domain-speciffc large language-vision assistant (PA-LLaVA) for pathology image understanding. Specifically, (1) we first construct a human pathology image-text dataset by cleaning the public medical image-text data for domainspecific alignment; (2) Using the proposed image-text data, we first train a pathology language-image pretraining (PLIP) model as the specialized visual encoder for pathology image, and then we developed scale-invariant connector to avoid the information loss caused by image scaling; (3) We adopt two-stage learning to train PA-LLaVA, first stage for domain alignment, and second stage for end to end visual question & answering (VQA) task.
|
10 |
|
|
|
|
|
11 |
## Architecture
|
12 |
|
13 |
![image](https://github.com/ddw2AIGROUP2CQUPT/PA-LLaVA/blob/main/xtuner_add/d285474a96a76781d5088a0a0dd85a3.png)
|
14 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
|
9 |
We developed a domain-speciffc large language-vision assistant (PA-LLaVA) for pathology image understanding. Specifically, (1) we first construct a human pathology image-text dataset by cleaning the public medical image-text data for domainspecific alignment; (2) Using the proposed image-text data, we first train a pathology language-image pretraining (PLIP) model as the specialized visual encoder for pathology image, and then we developed scale-invariant connector to avoid the information loss caused by image scaling; (3) We adopt two-stage learning to train PA-LLaVA, first stage for domain alignment, and second stage for end to end visual question & answering (VQA) task.
|
10 |
|
11 |
+
Our code is publicly available on Github.[ddw2AIGROUP2CQUPT/PA-LLaVA (github.com)](https://github.com/ddw2AIGROUP2CQUPT/PA-LLaVA)
|
12 |
+
|
13 |
## Architecture
|
14 |
|
15 |
![image](https://github.com/ddw2AIGROUP2CQUPT/PA-LLaVA/blob/main/xtuner_add/d285474a96a76781d5088a0a0dd85a3.png)
|
16 |
|
17 |
+
## Data Cleaning Process
|
18 |
+
|
19 |
+
|
20 |
+
|
21 |
+
Only the image names of the cleaned dataset are provided here, for the specific training code please visit our Github.
|
22 |
+
|
23 |
+
## contact
|
24 |
+
|
25 |
+
mailto: [[email protected]](mailto:[email protected]) or [[email protected]](mailto:[email protected])
|