Semantic Perturbations with Normalizing Flows for Improved Generalization

TL;DR

This paper introduces a novel data augmentation method using normalizing flows to generate semantically meaningful perturbations in the latent space, improving neural network generalization especially in low-data regimes.

Contribution

It leverages the reversible structure of normalizing flows for unsupervised, on-manifold perturbations, achieving state-of-the-art results on CIFAR-10/100 datasets.

Findings

Achieves 96.6% accuracy on CIFAR-10 with ResNet-18.

Outperforms existing augmentation methods, especially with limited data.

First to demonstrate latent-space perturbations improving real-world dataset performance.

Abstract

Data augmentation is a widely adopted technique for avoiding overfitting when training deep neural networks. However, this approach requires domain-specific knowledge and is often limited to a fixed set of hard-coded transformations. Recently, several works proposed to use generative models for generating semantically meaningful perturbations to train a classifier. However, because accurate encoding and decoding are critical, these methods, which use architectures that approximate the latent-variable inference, remained limited to pilot studies on small datasets. Exploiting the exactly reversible encoder-decoder structure of normalizing flows, we perform on-manifold perturbations in the latent space to define fully unsupervised data augmentations. We demonstrate that such perturbations match the performance of advanced data augmentation techniques -- reaching 96.6% test accuracy for CIFAR-10 using ResNet-18 and outperform existing methods, particularly in low data regimes -- yielding 10--25% relative improvement of test accuracy from classical training. We find that our latent adversarial perturbations adaptive to the classifier throughout its training are most effective, yielding the first test accuracy improvement results on real-world datasets -- CIFAR-10/100 -- via latent-space perturbations.