Kill Two Birds with One Stone: Rethinking Data Augmentation for Deep Long-tailed Learning

Binwu Wang, Pengkun Wang, Wei Xu, Xu Wang, Yudong Zhang, Kun Wang, Yang Wang

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: Long-tailed learning, data augmentation, imbalance, fairness

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: We find traditional augmentation strategies in long-tailed learning lead to an extrinsic augmentation-wise imbalance, so we propose a Dynamic Optional Data Augmentation to overcoming this intertwined imbalance.

Abstract: Real-world tasks are universally associated with training samples that exhibit a long-tailed class distribution, and traditional deep learning models are not suitable for fitting this distribution, thus resulting in a biased trained model. To surmount this dilemma, massive deep long-tailed learning studies have been proposed to achieve inter-class fairness models by designing sophisticated sampling strategies or improving existing model structures and loss functions. Habitually, these studies tend to apply data augmentation strategies to improve the generalization performance of their models. However, this augmentation strategy applied to balanced distributions may not be the best option for long-tailed distributions. For a profound understanding of data augmentation, we first theoretically analyze the gains of traditional augmentation strategies in long-tailed learning, and observe that augmentation methods cause the long-tailed distribution to be imbalanced again, resulting in an intertwined imbalance: inherent data-wise imbalance and extrinsic augmentation-wise imbalance, i.e., two 'birds' co-exist in long-tailed learning. Motivated by this observation, we propose an adaptive Dynamic Optional Data Augmentation (DODA) to address this intertwined imbalance, i.e., one 'stone' simultaneously 'kills' two 'birds', which allows each class to choose appropriate augmentation methods by maintaining a corresponding augmentation probability distribution for each class during training. Extensive experiments across mainstream long-tailed recognition benchmarks (e.g., CIFAR-100-LT, ImageNet-LT, and iNaturalist 2018) prove the effectiveness and flexibility of the DODA in overcoming the intertwined imbalance.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Primary Area: general machine learning (i.e., none of the above)

Submission Number: 7051