Skip to content

Repository files navigation

GENERATIVE ML for Data Augmentation

Overview

This project explores generative data augmentation to improve fine-grained image classification on a limited dataset of 75 butterfly species (5199 images). The main objective is to generate synthetic training data to boost a fixed baseline CNN classifier without modifying its architecture, optimizer, or loss function.

Authors

  • João Vaz
  • João Francisco Morais

Models Explored

We compared three generative families against the real-data baseline:

  • Variational AutoEncoders (VAEs)
  • Generative Adversarial Networks (GANs)
  • Denoising Diffusion Probabilistic Models (DDPMs)

Key Findings

Generation quality matters more than augmentation quantity. The final performance hierarchy is DDPM > GAN > Baseline > VAE:

  • DDPM: Best performance (+18.85 pp macro-F1, 86.61% accuracy) driven by superior image fidelity (FID 39.48).

  • GAN: Improved performance (+6.99 pp macro-F1), heavily relying on Adaptive Discriminator Augmentation (ADA) to prevent memorization.

  • VAE: Degraded classification (-2.72 pp macro-F1) due to blurry and washed-out generated textures.

About

VAEs GANs and DDPM for Data Augmentation

Topics

Resources

Stars

Watchers

Forks

Releases

Packages

Contributors

Languages