Balanced MSE for Imbalanced Visual Regression

Jiawei Ren, Mingyuan Zhang, Cunjun Yu, Ziwei Liu

S-Lab, Nanyang Technological University

School of Computing, National University of Singapore

CVPR 2022 (Oral Presentation)

Abstract

Data imbalance exists ubiquitously in real-world visual regressions, e.g., age estimation and pose estimation, hurting the model's generalizability and fairness. Thus, imbalanced regression gains increasing research attention recently. Compared to imbalanced classification, imbalanced regression focuses on continuous labels, which can be boundless and high-dimensional and hence more challenging. In this work, we identify that the widely used Mean Square Error (MSE) loss function can be ineffective in imbalanced regression. We revisit MSE from a statistical view and propose a novel loss function, Balanced MSE, to accommodate the imbalanced training label distribution. We further design multiple implementations of Balanced MSE to tackle different real-world scenarios, particularly including the one that requires no prior knowledge about the training label distribution. Moreover, to the best of our knowledge, Balanced MSE is the first general solution to high-dimensional imbalanced regression. Extensive experiments on both synthetic and three real-world benchmarks demonstrate the effectiveness of Balanced MSE.

Live Demo

Check out our live demo in the Hugging Face 🤗 space

Paper

Jiawei Ren, Mingyuan Zhang, Cunjun Yu, Ziwei Liu

Balanced MSE for Imbalanced Visual Regression

CVPR 2022 (Oral), [PDF], [Code]

BibTex

@inproceedings{ren2021bmse,

title={Balanced MSE for Imbalanced Visual Regression},

author={Ren, Jiawei and Zhang, Mingyuan and Yu, Cunjun and Liu, Ziwei},

booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},

year={2022}

}