Data Augmentation by Selecting Mixed Classes Considering Distance Between Classes
This work addresses a specific bottleneck in data augmentation for object recognition, offering an incremental improvement over existing methods.
The paper tackles the problem of random class selection in data augmentation methods like mixup by proposing a method that calculates inter-class distances and dynamically selects suitable classes for mixing based on training trends. The result is improved recognition performance on both general and long-tailed image recognition datasets.
Data augmentation is an essential technique for improving recognition accuracy in object recognition using deep learning. Methods that generate mixed data from multiple data sets, such as mixup, can acquire new diversity that is not included in the training data, and thus contribute significantly to accuracy improvement. However, since the data selected for mixing are randomly sampled throughout the training process, there are cases where appropriate classes or data are not selected. In this study, we propose a data augmentation method that calculates the distance between classes based on class probabilities and can select data from suitable classes to be mixed in the training process. Mixture data is dynamically adjusted according to the training trend of each class to facilitate training. The proposed method is applied in combination with conventional methods for generating mixed data. Evaluation experiments show that the proposed method improves recognition performance on general and long-tailed image recognition datasets.