ADLDA: A Method to Reduce the Harm of Data Distribution Shift in Data Augmentation
This addresses the issue of reduced model robustness and accuracy due to distribution shifts in data augmentation for computer vision, offering an incremental improvement as a regularization method.
The paper tackles the problem of data distribution shifts caused by data augmentation in computer vision by introducing ADLDA, a method that partitions augmented data into subdomains and uses domain adaptation, resulting in significant performance enhancements across multiple datasets, particularly in complex neural networks.
This study introduces a novel data augmentation technique, ADLDA, aimed at mitigating the negative impact of data distribution shifts caused by the data augmentation process in computer vision task. ADLDA partitions augmented data into distinct subdomains and incorporates domain labels, combined with domain adaptation techniques, to optimize data representation in the model's feature space. Experimental results demonstrate that ADLDA significantly enhances model performance across multiple datasets, particularly in neural network architectures with complex feature extraction layers. Furthermore, ADLDA improves the model's ability to locate and recognize key features, showcasing potential in object recognition and image segmentation tasks. This paper's contribution provides an effective data augmentation regularization method for the field of computer vision aiding in the enhancement of robustness and accuracy in deep learning models.