Model card
Browse files
README.md
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: en
|
| 3 |
+
license: cc-by-nc-4.0
|
| 4 |
+
tags:
|
| 5 |
+
- medical
|
| 6 |
+
- vqa
|
| 7 |
+
- gastrointestinal
|
| 8 |
+
- endoscopy
|
| 9 |
+
- lora
|
| 10 |
+
- task2
|
| 11 |
+
datasets:
|
| 12 |
+
- SimulaMet/Kvasir-VQA-x1
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
# MEDVQA-GI-2026-Task2-Explainability
|
| 16 |
+
|
| 17 |
+
Models fine-tuned for **ImageCLEFmed MEDVQA-GI 2026 — Subtask 2: Multimodal Explainability & Safety-Aware Reasoning**.
|
| 18 |
+
|
| 19 |
+
## Results
|
| 20 |
+
|
| 21 |
+
| Model | Token-F1 | BERTScore-F1 | Safety-Score | Halluc-Rate | ECE |
|
| 22 |
+
|------------|------------|------------|------------|------------|------------|
|
| 23 |
+
| MedGemma-KvasirFT | 0.4891 | 0.5602 | 0.7150 | 0.2880 | 0.8537 |
|
| 24 |
+
| Qwen2.5-VL-KvasirFT | 0.4967 | 0.5817 | 0.8511 | 0.3680 | 0.6838 |
|
| 25 |
+
| Qwen2.5-VL-TransfFT | 0.4954 | 0.5793 | 0.8401 | 0.3780 | 0.7016 |
|
| 26 |
+
| Qwen2.5-VL-Base | 0.4292 | 0.5174 | 0.8175 | 0.4560 | 0.7241 |
|
| 27 |
+
| Hybrid | 0.4456 | 0.5342 | 0.8309 | 0.3280 | 0.7359 |
|
| 28 |
+
|
| 29 |
+
**Best model**: Qwen2.5-VL-KvasirFT
|