Skip to content

allenjoshua16/ViT-Robustness-Lab

Repository files navigation

ViT Robustness Lab

An interactive AI-powered web application for exploring the robustness of Vision Transformers through attention map visualization and adversarial attack simulations.

Overview

ViT Robustness Lab helps users understand how Vision Transformer models respond to clean and perturbed images. The app provides a visual interface to study attention behavior, compare prediction confidence, and simulate robustness failures in a more interpretable way.

Key Features

  • Vision Transformer robustness analysis
  • Real-time attention map visualization
  • Adversarial attack simulation
  • Clean vs perturbed image comparison
  • AI-assisted explanations using Google AI Studio / Gemini
  • Interactive frontend built with React, Vite, and TypeScript

Tech Stack

  • React
  • TypeScript
  • Vite
  • Node.js / Express
  • Google Gemini API
  • Google AI Studio
  • Render

Contributors

Acknowledgments

  • Google AI Studio (Gemini) for AI-assisted development

Project Structure

ViT-Robustness-Lab/
├── src/
├── server.ts
├── index.html
├── package.json
├── vite.config.ts
├── tsconfig.json
├── .env.example
└── README.md

About

An interactive lab for analyzing Vision Transformer robustness through real-time attention map visualization and adversarial attack simulations.

Topics

Resources

License

Contributing

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors