DBN-Mix: Training Dual Branch Network Using Bilateral Mixup Augmentation for Long-Tailed Visual Recognition
This addresses the challenge of class imbalance in visual recognition for applications like image classification, though it appears incremental as it builds on existing dual-branch network frameworks.
The paper tackles the problem of long-tailed visual recognition by proposing DBN-Mix, a method that uses bilateral mixup augmentation and class-wise temperature scaling to improve representation learning for minority classes, achieving state-of-the-art performance in some benchmark categories.
There is growing interest in the challenging visual perception task of learning from long-tailed class distributions. The extreme class imbalance in the training dataset biases the model to prefer recognizing majority class data over minority class data. Furthermore, the lack of diversity in minority class samples makes it difficult to find a good representation. In this paper, we propose an effective data augmentation method, referred to as bilateral mixup augmentation, which can improve the performance of long-tailed visual recognition. The bilateral mixup augmentation combines two samples generated by a uniform sampler and a re-balanced sampler and augments the training dataset to enhance the representation learning for minority classes. We also reduce the classifier bias using class-wise temperature scaling, which scales the logits differently per class in the training phase. We apply both ideas to the dual-branch network (DBN) framework, presenting a new model, named dual-branch network with bilateral mixup (DBN-Mix). Experiments on popular long-tailed visual recognition datasets show that DBN-Mix improves performance significantly over baseline and that the proposed method achieves state-of-the-art performance in some categories of benchmarks.