Update README.md
Browse files
README.md
CHANGED
|
@@ -26,9 +26,9 @@ It combines post text with **image captions generated** by [`Salesforce/blip-ima
|
|
| 26 |
|
| 27 |
## 📊 Results
|
| 28 |
|
| 29 |
-
| Approach | Accuracy | Macro F1-Score |
|
| 30 |
-
|
| 31 |
-
| Text + Caption | **0.87** | **0.83** |
|
| 32 |
|
| 33 |
⚡️ Using captions instead of raw image features leads to state-of-the-art performance on Fakeddit, with simpler input and no vision backbone needed during inference.
|
| 34 |
|
|
|
|
| 26 |
|
| 27 |
## 📊 Results
|
| 28 |
|
| 29 |
+
| Approach | Accuracy | Macro F1-Score |
|
| 30 |
+
|------------------|----------|----------------|
|
| 31 |
+
| Text + Caption | **0.87** | **0.83** |
|
| 32 |
|
| 33 |
⚡️ Using captions instead of raw image features leads to state-of-the-art performance on Fakeddit, with simpler input and no vision backbone needed during inference.
|
| 34 |
|