ImageShield-SUPER-90M

ImageShield-SUPER-90M is a vision-language image classification model based on google/siglip2-base-patch16-224, trained on 100K samples from the ImageShield-Guardrail Safe and Unsafe Images dataset. Built on the SiglipForImageClassification architecture, the model is designed to classify visual content as Safe or Unsafe for content moderation and media filtering.

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

This model is experimental. Expert VLMs are coming soon: ImageShield Multimodal SFT Collection.

Label Space: 2 Classes

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

Class 0: "Safe"
Class 1: "Unsafe"

Install Dependencies

pip install transformers torch torchvision pillow gradio

Inference Code

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

# Load model and processor
model_name = "prithivMLmods/ImageShield-SUPER-90M"
model = SiglipForImageClassification.from_pretrained(model_name)
processor = AutoImageProcessor.from_pretrained(model_name)

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

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="ImageShield-SUPER-90M",
    description="Classifies images as Safe or Unsafe."
)

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

Intended Use

This model is intended for applications such as:

• Content Moderation: Identify unsafe visual content.
• Parental Controls: Support AI-based media filtering.
• Dataset Preprocessing: Categorize and filter safe and unsafe images.
• Online Platforms: Assist with content safety and upload moderation.
• AI Image Applications: Provide an additional safety layer for image generation and editing workflows.

Classification Report

Training vs Evaluation Loss / Accuracy

Precision / Recall / F1-score per Class

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.