Update README.md
Browse files
README.md
CHANGED
|
@@ -28,8 +28,6 @@ It combines post text with **image captions generated** by [`Salesforce/blip-ima
|
|
| 28 |
|
| 29 |
| Approach | Accuracy | Macro F1-Score | Source |
|
| 30 |
|------------------|----------|----------------|-----------------------|
|
| 31 |
-
| Text | 0.76 | – | Nakamura et al., 2020 |
|
| 32 |
-
| Text + Image | 0.85 | – | Nakamura et al., 2020 |
|
| 33 |
| Text + Caption | **0.87** | **0.83** | This work |
|
| 34 |
|
| 35 |
⚡️ 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.
|
|
|
|
| 28 |
|
| 29 |
| Approach | Accuracy | Macro F1-Score | Source |
|
| 30 |
|------------------|----------|----------------|-----------------------|
|
|
|
|
|
|
|
| 31 |
| Text + Caption | **0.87** | **0.83** | This work |
|
| 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.
|