OnlineAugment: Online Data Augmentation with Less Domain Knowledge

Abstract

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. Code is available at https://github.com/zhiqiangdon/online-augment .

ECCV2020

References in corpus (15)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• mixup: Beyond Empirical Risk Minimization
• Neural Architecture Search with Reinforcement Learning
• R-FCN: Object Detection via Region-based Fully Convolutional Networks
• Improved Regularization of Convolutional Neural Networks with Cutout
• Wide Residual Networks
• The Liver Tumor Segmentation Benchmark (LiTS)
• Data Augmentation Generative Adversarial Networks
• Meta-Learning for Semi-Supervised Few-Shot Classification
• Shake-Shake regularization
• Adversarial Training Can Hurt Generalization
• Stochastic Hyperparameter Optimization through Hypernetworks
• Adversarial Examples Improve Image Recognition
• Efficient Two-Step Adversarial Defense for Deep Neural Networks