Update README.md
Browse files
README.md
CHANGED
|
@@ -16,6 +16,9 @@ tags:
|
|
| 16 |
|
| 17 |
> **Face-Confidence-SigLIP2** is a vision-language encoder model fine-tuned from **google/siglip2-base-patch16-224** for **binary image classification**. It is trained to distinguish between images of **confident faces** and **unconfident faces** using the **SiglipForImageClassification** architecture.
|
| 18 |
|
|
|
|
|
|
|
|
|
|
| 19 |
```py
|
| 20 |
Classification report:
|
| 21 |
|
|
|
|
| 16 |
|
| 17 |
> **Face-Confidence-SigLIP2** is a vision-language encoder model fine-tuned from **google/siglip2-base-patch16-224** for **binary image classification**. It is trained to distinguish between images of **confident faces** and **unconfident faces** using the **SiglipForImageClassification** architecture.
|
| 18 |
|
| 19 |
+
> [!note]
|
| 20 |
+
*SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features* https://arxiv.org/pdf/2502.14786
|
| 21 |
+
|
| 22 |
```py
|
| 23 |
Classification report:
|
| 24 |
|