LA3: Efficient Label-Aware AutoAugment
arXiv:2304.10310 · doi:10.1007/978-3-031-19803-8_16
Abstract
Automated augmentation is an emerging and effective technique to search for data augmentation policies to improve generalizability of deep neural network training. Most existing work focuses on constructing a unified policy applicable to all data samples in a given dataset, without considering sample or class variations. In this paper, we propose a novel two-stage data augmentation algorithm, named Label-Aware AutoAugment (LA3), which takes advantage of the label information, and learns augmentation policies separately for samples of different labels. LA3 consists of two learning stages, where in the first stage, individual augmentation methods are evaluated and ranked for each label via Bayesian Optimization aided by a neural predictor, which allows us to identify effective augmentation techniques for each label under a low search cost. And in the second stage, a composite augmentation policy is constructed out of a selection of effective as well as complementary augmentations, which produces significant performance boost and can be easily deployed in typical model training. Extensive experiments demonstrate that LA3 achieves excellent performance matching or surpassing existing methods on CIFAR-10 and CIFAR-100, and achieves a new state-of-the-art ImageNet accuracy of 79.97% on ResNet-50 among auto-augmentation methods, while maintaining a low computational cost.
arXiv commentECCV 2022
References in corpus (10)
- Adam: A Method for Stochastic Optimization
- mixup: Beyond Empirical Risk Minimization
- Categorical Reparameterization with Gumbel-Softmax
- Improved Regularization of Convolutional Neural Networks with Cutout
- Data Augmentation by Pairing Samples for Images Classification
- Shake-Shake regularization
- Population Based Training of Neural Networks
- Adversarial AutoAugment
- DADA: Differentiable Automatic Data Augmentation
- Improving Auto-Augment via Augmentation-Wise Weight Sharing