Universal Adaptive Data Augmentation

TL;DR

Universal Adaptive Data Augmentation (UADA) dynamically updates augmentation parameters during training based on model gradients, leading to improved generalization across multiple vision tasks and datasets.

Contribution

UADA introduces a novel adaptive strategy that updates data augmentation parameters during training using gradient information, enhancing model robustness and performance.

Findings

Significant performance improvements on CIFAR-10 and CIFAR-100.

Effective across various tasks like image classification, segmentation, and detection.

Proven on multiple datasets including ImageNet and Cityscapes.

Abstract

Existing automatic data augmentation (DA) methods either ignore updating DA's parameters according to the target model's state during training or adopt update strategies that are not effective enough. In this work, we design a novel data augmentation strategy called "Universal Adaptive Data Augmentation" (UADA). Different from existing methods, UADA would adaptively update DA's parameters according to the target model's gradient information during training: given a pre-defined set of DA operations, we randomly decide types and magnitudes of DA operations for every data batch during training, and adaptively update DA's parameters along the gradient direction of the loss concerning DA's parameters. In this way, UADA can increase the training loss of the target networks, and the target networks would learn features from harder samples to improve the generalization. Moreover, UADA is very general and can be utilized in numerous tasks, e.g., image classification, semantic segmentation and object detection. Extensive experiments with various models are conducted on CIFAR-10, CIFAR-100, ImageNet, tiny-ImageNet, Cityscapes, and VOC07+12 to prove the significant performance improvements brought by UADA.