Optimal Layer Selection for Latent Data Augmentation
This work addresses the issue of optimizing feature augmentation for researchers and practitioners in computer vision, though it is incremental as it builds on existing latent DA methods.
The study tackled the problem of arbitrary layer selection for latent data augmentation in neural networks by investigating trends of suitable layers and proposing an adaptive method (AdaLASE) that updates DA ratios per layer via gradient descent, achieving high overall test accuracy on image classification datasets.
While data augmentation (DA) is generally applied to input data, several studies have reported that applying DA to hidden layers in neural networks, i.e., feature augmentation, can improve performance. However, in previous studies, the layers to which DA is applied have not been carefully considered, often being applied randomly and uniformly or only to a specific layer, leaving room for arbitrariness. Thus, in this study, we investigated the trends of suitable layers for applying DA in various experimental configurations, e.g., training from scratch, transfer learning, various dataset settings, and different models. In addition, to adjust the suitable layers for DA automatically, we propose the adaptive layer selection (AdaLASE) method, which updates the ratio to perform DA for each layer based on the gradient descent method during training. The experimental results obtained on several image classification datasets indicate that the proposed AdaLASE method altered the ratio as expected and achieved high overall test accuracy.