Watermark-Detection-SigLIP2

Watermark-Detection-SigLIP2 is a vision-language encoder model fine-tuned from google/siglip2-base-patch16-224 for binary image classification.
It detects whether an image contains a watermark or not, using the SiglipForImageClassification architecture.

⚠️ Note: Watermark detection works best with high-quality, crisp images. Avoid noisy inputs.

📄 Paper: SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
https://arxiv.org/pdf/2502.14786

---

📊 Classification Report

              precision    recall  f1-score   support

No Watermark     0.9290    0.9722    0.9501     12779
   Watermark     0.9622    0.9048    0.9326      9983

    accuracy                         0.9427     22762
   macro avg     0.9456    0.9385    0.9414     22762
weighted avg     0.9435    0.9427    0.9424     22762