LatentAugment: Dynamically Optimized Latent Probabilities of Data Augmentation
This work addresses the challenge of selecting effective data augmentation strategies for image classification tasks, which is crucial for improving model performance in computer vision applications, and it presents an incremental advancement by dynamically optimizing augmentation policies.
The paper tackles the problem of identifying optimal data augmentation policies for image classification by proposing LatentAugment, a method that dynamically estimates and optimizes latent probabilities of augmentation for each input and model parameter, achieving higher test accuracy than previous methods on CIFAR-10, CIFAR-100, SVHN, and ImageNet datasets.
Although data augmentation is a powerful technique for improving the performance of image classification tasks, it is difficult to identify the best augmentation policy. The optimal augmentation policy, which is the latent variable, cannot be directly observed. To address this problem, this study proposes $\textit{LatentAugment}$, which estimates the latent probability of optimal augmentation. The proposed method is appealing in that it can dynamically optimize the augmentation strategies for each input and model parameter in learning iterations. Theoretical analysis shows that LatentAugment is a general model that includes other augmentation methods as special cases, and it is simple and computationally efficient in comparison with existing augmentation methods. Experimental results show that the proposed LatentAugment has higher test accuracy than previous augmentation methods on the CIFAR-10, CIFAR-100, SVHN, and ImageNet datasets.