Update README.md
Browse files
README.md
CHANGED
|
@@ -39,6 +39,11 @@ weighted avg 0.9991 0.9991 0.9991 11832
|
|
| 39 |
|
| 40 |
---
|
| 41 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
## **Label Space: 2 Classes**
|
| 43 |
|
| 44 |
The model classifies each input image into one of the following categories:
|
|
|
|
| 39 |
|
| 40 |
---
|
| 41 |
|
| 42 |
+
> [!note]
|
| 43 |
+
*SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features* https://arxiv.org/pdf/2502.14786
|
| 44 |
+
|
| 45 |
+
---
|
| 46 |
+
|
| 47 |
## **Label Space: 2 Classes**
|
| 48 |
|
| 49 |
The model classifies each input image into one of the following categories:
|