CUDA: Curriculum of Data Augmentation for Long-tailed Recognition Download PDF

05 Oct 2022, 00:12 (modified: 04 Nov 2022, 01:09)NeurIPS 2022 Workshop DistShift PosterReaders: Everyone
Keywords: long-tailed recognition, class imbalance
TL;DR: We propose a class-wise data augmentation method by designing the curriculum of data augmentation, which is based on our findings that stronger augmentation on major classes improves the performance on long-tailed recognition.
Abstract: Class imbalance problems frequently occur in real-world tasks, and conventional deep learning algorithms are well known for performance degradation on imbalanced training datasets. To mitigate this problem, many approaches have aimed to balance among given classes by re-weighting or re-sampling training samples. These re-balancing methods increase the impact of minority classes and reduce the influence of majority classes on the output of models. Despite extensive recent studies, no deep analysis has been conducted on determination of classes to be augmented and strength of augmentation has been conducted. In this study, we propose a simple and efficient novel curriculum, which is designed to find the appropriate per-class strength of data augmentation, called CUDA: CUrriculum of Data Augmentation for long-tailed recognition. CUDA can simply be integrated into existing long-tailed recognition methods. We present the results of experiments showing that CUDA effectively achieves better generalization performance compared to the state-of-the-art method on imbalanced datasets such as CIFAR-100-LT.
1 Reply