Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- chest-xray
|
| 4 |
+
- radiology
|
| 5 |
+
- visual-question-answering
|
| 6 |
+
- differential-vqa
|
| 7 |
+
- mimic-cxr
|
| 8 |
+
license: apache-2.0
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# LAPVQA — Differential VQA (Captioning-Pretrained Encoder)
|
| 12 |
+
|
| 13 |
+
Part of the [LAPVQA collection](https://huggingface.co/collections/dmusingu/lapvqa).
|
| 14 |
+
|
| 15 |
+
## Description
|
| 16 |
+
|
| 17 |
+
DiffVQA task head trained on top of the **LAPVQA captioning-pretrained encoder**
|
| 18 |
+
([`lapvqa-pretrain-captioning`](https://huggingface.co/dmusingu/lapvqa-pretrain-captioning)).
|
| 19 |
+
The encoder is kept frozen; this file contains the task head only.
|
| 20 |
+
|
| 21 |
+
## Results (test set)
|
| 22 |
+
|
| 23 |
+
| BLEU-4 | ROUGE-2 | RadGraph-s | BERTScore F1 |
|
| 24 |
+
|---|---|---|---|
|
| 25 |
+
| 0.468 | 0.562 | 0.303 | 0.938 |
|
| 26 |
+
|
| 27 |
+
## Files
|
| 28 |
+
|
| 29 |
+
| File | Description |
|
| 30 |
+
|---|---|
|
| 31 |
+
| `pretrain-captioning_best.pt` | DiffVQA head (encoder not included) |
|