🧠 Enhanced Multi-Model Image Classifier

Features: Adversarial Examples | Class-Specific Attention | 13+ Models

📸 Upload Image

🤖 Select Model

🎭 Adversarial Noise

Noise Level (ε)

Add random noise to test model robustness

0 0.3

🎯 Top 5 Predictions

🔍 Attention Map (Top Prediction)

🎨 Class-Specific Attention Visualization

Type any class name to see where the model looks for that specific object

🔍 Enter Class Name

Type any ImageNet class name

💡 Sample classes to try:

Click to auto-fill

cat dog tiger lion elephant car truck airplane ship train pizza hamburger coffee banana apple chair table laptop keyboard mouse person bicycle building tree flower

🔍 Class-Specific Attention Map

Status

💡 Tips:

Adversarial Noise: Adjust the slider to add random noise and see how robust the model is
Class-Specific Attention: Type any ImageNet class to visualize what the model looks for
Model Variety: Try different architectures (ViT, CNN, Hybrid) to compare their behavior

·

Built with Gradio logo

·

·