SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2108.07958 · ICCV · 2021

Semantic Perturbations with Normalizing Flows for Improved Generalization

Martin Jaggi, Sebastian Stich, Tatjana Chavdarova, Oguz Kaan

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2108.07958")
get_code_for_paper("2108.07958")
have("2108.07958")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2108.07958.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2108.07958.svg)](https://syntology.ai/paper/2108.07958)

Connect an agent — have() is free.