DBN-Mix: Training Dual Branch Network Using Bilateral Mixup Augmentation for Long-Tailed Visual Recognition

by   Jae Soon Baik, et al.

There is a 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 to recognize majority-class data over minority-class data. Recently, the dual branch network (DBN) framework has been proposed, where two branch networks; the conventional branch and the re-balancing branch were employed to improve the accuracy of long-tailed visual recognition. The re-balancing branch uses a reverse sampler to generate class-balanced training samples to mitigate bias due to class imbalance. Although this strategy has been quite successful in handling bias, using a reversed sampler for training can degrade the representation learning performance. To alleviate this issue, the conventional method used a carefully designed cumulative learning strategy, in which the influence of the re-balancing branch gradually increases throughout the entire training phase. In this study, we aim to develop a simple yet effective method to improve the performance of DBN without cumulative learning that is difficult to optimize. We devise a simple data augmentation method termed bilateral mixup augmentation, which combines one sample from the uniform sampler with another sample from the reversed sampler to produce a training sample. Furthermore, we present class-conditional temperature scaling that mitigates bias toward the majority class for the proposed DBN architecture. Our experiments performed on widely used long-tailed visual recognition datasets show that bilateral mixup augmentation is quite effective in improving the representation learning performance of DBNs, and that the proposed method achieves state-of-the-art performance for some categories.


page 1

page 2

page 3

page 4


BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition

Our work focuses on tackling the challenging but natural visual recognit...

Dual-Branch Network with Dual-Sampling Modulated Dice Loss for Hard Exudate Segmentation from Colour Fundus Images

Automated segmentation of hard exudates in colour fundus images is a cha...

CUDA: Curriculum of Data Augmentation for Long-Tailed Recognition

Class imbalance problems frequently occur in real-world tasks, and conve...

VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognition

Deep learning-based models encounter challenges when processing long-tai...

Towards Calibrated Model for Long-Tailed Visual Recognition from Prior Perspective

Real-world data universally confronts a severe class-imbalance problem a...

Delving into Semantic Scale Imbalance

Model bias triggered by long-tailed data has been widely studied. Howeve...

Relieving Long-tailed Instance Segmentation via Pairwise Class Balance

Long-tailed instance segmentation is a challenging task due to the extre...

Please sign up or login with your details

Forgot password? Click here to reset