SigLIP2-ImageShield-2n-large-256 is a vision-language encoder model fine-tuned from google/siglip2-large-patch16-256 for binary image classification. Built on the SiglipForImageClassification architecture, the model is designed to identify and categorize visual content into safe/normal and unsafe/sensual categories for media filtering.

[!IMPORTANT] This model is experimental. Expert multimodal models are available here: ImageShield Multimodal SFT Collection.

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

Label Space: 2 Classes

The model classifies each image into one of the following content categories:

text

Class 0: "Safe and Normal"
Class 1: "Unsafe and Sensual"

Install Dependencies

pip install transformers torch torchvision pillow gradio

Inference Code

python

import gradio as gr
from transformers import AutoImageProcessor, SiglipForImageClassification
from PIL import Image
import torch

# Load model and processor
model_name = "prithivMLmods/SigLIP2-ImageShield-2n-large-256"  # Replace with your model path if needed
model = SiglipForImageClassification.from_pretrained(model_name)
processor = AutoImageProcessor.from_pretrained(model_name)

# ID to Label mapping
id2label = {
    "0": "Safe and Normal",
    "1": "Unsafe and Sensual"
}

def classify_image(image):
    image = Image.fromarray(image).convert("RGB")
    inputs = processor(images=image, return_tensors="pt")

    with torch.no_grad():
        outputs = model(**inputs)
        logits = outputs.logits
        probs = torch.nn.functional.softmax(logits, dim=1).squeeze().tolist()

    prediction = {
        id2label[str(i)]: round(probs[i], 3)
        for i in range(len(probs))
    }

    return prediction

# Gradio Interface
iface = gr.Interface(
    fn=classify_image,
    inputs=gr.Image(type="numpy"),
    outputs=gr.Label(
        num_top_classes=2,
        label="Predicted Content Type"
    ),
    title="SigLIP2-ImageShield-2n-large-256",
    description="Classifies images into Safe and Normal or Unsafe and Sensual categories."
)

if __name__ == "__main__":
    iface.launch()

Intended Use

This model is intended for applications such as:

Content Moderation: Identify unsafe or sensual visual content.
Parental Controls: Support AI-based media filtering.
Dataset Preprocessing: Categorize and filter image datasets.
Online Platforms: Assist with content safety and upload moderation.

Classification Report

Training vs Evaluation Loss / Accuracy

Training vs Evaluation Loss and Accuracy

Precision / Recall / F1-score per Class

Per-Class Precision, Recall, and F1-score

Confusion Matrix

Test Set Class Distribution

Overall Prediction Accuracy

Misalignment Distribution by True Class

Acknowledgements

Transformers: Transformers provides state-of-the-art machine learning models for text, computer vision, audio, video, and multimodal tasks, supporting both inference and training.
SigLIP 2: Multilingual vision-language encoders with improved semantic understanding, localization, and dense feature representations.