Mining latent labels for imbalance classification: a regrouping perspective

Yash Travadi, Le Peng, Ying Cui, Rui Zhang, Ju Sun

Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning

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: imbalanced learning, supervised learning, image classification

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

Abstract: Deep learning-based models are sensitive to class imbalance. Existing approaches often involve rebalancing tricks such as loss reweighting and class resampling to emphasize the minority class. In this work, we explore a novel baseline method to deal with class imbalance by regrouping the majority class into smaller pseudo-classes and turning the imbalanced classification problem into a balanced multiclass classification. This simple modification helps to make the class frequencies more uniform in the training data and, simultaneously, helps the representation learning by imposing a structure on the majority class. Experiment results on binary and multiclass classification show that the proposed method can substantially boost the classification performance as measured by average precision metric. Our code will be released before publication.

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.

Submission Number: 4181