Implicit Semantic Data Augmentation for Deep Networks

TL;DR

This paper introduces ISDA, a semantic data augmentation method that leverages the linearization of deep features to improve model generalization without significant computational overhead.

Contribution

We propose a novel implicit semantic data augmentation technique that estimates intra-class feature covariance and directly minimizes a robust cross-entropy loss, enhancing deep network performance.

Findings

ISDA improves accuracy on CIFAR-10, CIFAR-100, and ImageNet datasets.

The method adds negligible computational cost to standard training.

ISDA consistently outperforms traditional augmentation techniques.

Abstract

In this paper, we propose a novel implicit semantic data augmentation (ISDA) approach to complement traditional augmentation techniques like flipping, translation or rotation. Our work is motivated by the intriguing property that deep networks are surprisingly good at linearizing features, such that certain directions in the deep feature space correspond to meaningful semantic transformations, e.g., adding sunglasses or changing backgrounds. As a consequence, translating training samples along many semantic directions in the feature space can effectively augment the dataset to improve generalization. To implement this idea effectively and efficiently, we first perform an online estimate of the covariance matrix of deep features for each class, which captures the intra-class semantic variations. Then random vectors are drawn from a zero-mean normal distribution with the estimated covariance to augment the training data in that class. Importantly, instead of augmenting the samples explicitly, we can directly minimize an upper bound of the expected cross-entropy (CE) loss on the augmented training set, leading to a highly efficient algorithm. In fact, we show that the proposed ISDA amounts to minimizing a novel robust CE loss, which adds negligible extra computational cost to a normal training procedure. Although being simple, ISDA consistently improves the generalization performance of popular deep models (ResNets and DenseNets) on a variety of datasets, e.g., CIFAR-10, CIFAR-100 and ImageNet. Code for reproducing our results is available at https://github.com/blackfeather-wang/ISDA-for-Deep-Networks.