Data Augmentation by Selecting Mixed Classes Considering Distance Between Classes
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Data AugmentationDiversityObject RecognitionSimilar Papers 제목 키워드 기반
Non-exemplar Class-incremental Learning by Random Auxiliary Classes Augmentation and Mixed Features
Non-exemplar class-incremental learning refers to classifying new and old classes without storing samples of old classes. Since only new class samples are available for optimization, it often occurs catastrophic forgetti…
class-incremental learningClass Incremental LearningIncremental LearningThe Effects of Mixed Sample Data Augmentation are Class Dependent
Mixed Sample Data Augmentation (MSDA) techniques, such as Mixup, CutMix, and PuzzleMix, have been widely acknowledged for enhancing performance in a variety of tasks. A previous study reported the class dependency of tra…
Data AugmentationMiAMix: Enhancing Image Classification through a Multi-stage Augmented Mixed Sample Data Augmentation Method
Despite substantial progress in the field of deep learning, overfitting persists as a critical challenge, and data augmentation has emerged as a particularly promising approach due to its capacity to enhance model genera…
Computational EfficiencyData AugmentationImage Augmentationimage-classification+1Improved Mixed-Example Data Augmentation
In order to reduce overfitting, neural networks are typically trained with data augmentation, the practice of artificially generating additional training data via label-preserving transformations of existing training exa…
Data AugmentationImage AugmentationAugmented Balanced Image Dataset Generator Using AugStatic Library
The mixed data consists of various structured and unstructured data. The exponential boom of the amount of data has made the datasets of varying samples. This paper focuses on the image dataset generator that balances an…
ClassificationData AugmentationData VisualizationDetecting Image Manipulation+13