OnlineAugment: Online Data Augmentation with Less Domain Knowledge

by   Zhiqiang Tang, et al.

Data augmentation is one of the most important tools in training modern deep neural networks. Recently, great advances have been made in searching for optimal augmentation policies in the image classification domain. However, two key points related to data augmentation remain uncovered by the current methods. First is that most if not all modern augmentation search methods are offline and learning policies are isolated from their usage. The learned policies are mostly constant throughout the training process and are not adapted to the current training model state. Second, the policies rely on class-preserving image processing functions. Hence applying current offline methods to new tasks may require domain knowledge to specify such kind of operations. In this work, we offer an orthogonal online data augmentation scheme together with three new augmentation networks, co-trained with the target learning task. It is both more efficient, in the sense that it does not require expensive offline training when entering a new domain, and more adaptive as it adapts to the learner state. Our augmentation networks require less domain knowledge and are easily applicable to new tasks. Extensive experiments demonstrate that the proposed scheme alone performs on par with the state-of-the-art offline data augmentation methods, as well as improving upon the state-of-the-art in combination with those methods.


Learning Data Augmentation with Online Bilevel Optimization for Image Classification

Data augmentation is a key practice in machine learning for improving ge...

GABO: Graph Augmentations with Bi-level Optimization

Data augmentation refers to a wide range of techniques for improving mod...

Greedy AutoAugment

A major problem in data augmentation is the number of possibilities in t...

Learning unfolded networks with a cyclic group structure

Deep neural networks lack straightforward ways to incorporate domain kno...

Hard Regularization to Prevent Collapse in Online Deep Clustering without Data Augmentation

Online deep clustering refers to the joint use of a feature extraction n...

Automatically Learning Data Augmentation Policies for Dialogue Tasks

Automatic data augmentation (AutoAugment) (Cubuk et al., 2019) searches ...

DNA: Dynamic Network Augmentation

In many classification problems, we want a classifier that is robust to ...

Please sign up or login with your details

Forgot password? Click here to reset