A Group-Theoretic Framework for Data Augmentation

By Shuxiao Chen, Edgar Dobriban, Jane Lee. 2019

241 citations recorded by the source corpus.

Subfields: Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Representation & Self-Supervised Learning

Citations in the corpus

A Survey of Data Augmentation Approaches for NLP (2021, background): “Chen et al. (2020d) show that DA leads to variance reduction by averaging over orbits of the group that keep the data distribution approximately invariant.”
UniformAugment: A Search-free Probabilistic Data Augmentation Approach (2020, methodology): “In addition to extensive experiments, we also analyzed our method and other automated augmentation methods using the theoretical framework proposed by Chen et al. [2].”
Repeated Augmented Rehearsal: A Simple but Strong Baseline for Online Continual Learning (2022, background): “learning setting, Chen et al. [2020] found that such an orbit-averaging operation can reduce both the variance and generalization error.”
MedViT: A Robust Vision Transformer for Generalized Medical Image Classification (2023, result): “Moreover, a rich data augmentation also helps with robustness and generalization, which has been verified in previous works [17, 61, 62].”
Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style (2021, background): “While this intuitively makes sense and has shown remarkable empirical results, the success of data augmentation techniques in practice is still not very well understood from a theoretical perspective—despite some efforts [17, 19, 28].”
A Comprehensive Survey of Image Augmentation Techniques for Deep Learning (2022, methodology): “Recently, kernel theory [102] and group theory [103] have been used to analyze the eﬀects of image augmentation.”
Data Augmentation Approaches in Natural Language Processing: A Survey (2021, background): “The few related works are of DA in the image domain, considering data augmentation as encoding a priori knowledge about data or task invariance [140], variance reduction [141] or regularization methods [142].”
On the Generalization Effects of Linear Transformations in Data Augmentation (2020, background): “Previous work has analyzed the effect of Gaussian augmentation (Rajput et al., 2019) and feature averaging effect of adding transformed data (Dao et al., 2019; Chen et al., 2019).”
Adversarial Robustness with Semi-Infinite Constrained Learning (2021, methodology): “Yet, by once again ﬁxing the pertubation distribution λ , we can obtain a myriad of data augmentation techniques, including the group-theoretic data-augmentation scheme discussed in [93], where G denotes the group action, and the model-based robust training methods discussed in [62–65].”