Post-Training Augmentation Invariance
Researchers have developed a new framework for post-training augmentation invariance, allowing pretrained neural networks to gain new invariance properties without affecting their performance on original data. This method uses lightweight adapter networks appended to the latent space, trained with novel Markov-Wasserstein minimization or Wasserstein correlation maximization losses. Empirical results show significant improvements in classification accuracy for rotated and noisy images, with minimal corruption to the original features and no fine-tuning of the base network. AI
IMPACT Enables models to generalize better to augmented data without performance degradation on original inputs.