Delving into Deep Imbalanced Regression

Yuzhe Yang1      Kaiwen Zha1      Ying-Cong Chen1      Hao Wang2      Dina Katabi1
1 MIT CSAIL      2 Rutgers University


Real-world data often exhibit imbalanced distributions, where certain target values have significantly fewer observations. Existing techniques for dealing with imbalanced data focus on targets with categorical indices, i.e., different classes. However, many tasks involve continuous targets, where hard boundaries between classes do not exist. We define Deep Imbalanced Regression (DIR) as learning from such imbalanced data with continuous targets, dealing with potential missing data for certain target values, and generalizing to the entire target range. Motivated by the intrinsic difference between categorical and continuous label space, we propose distribution smoothing for both labels and features, which explicitly acknowledges the effects of nearby targets, and calibrates both label and learned feature distributions. We curate and benchmark large-scale DIR datasets from common real-world tasks in computer vision, natural language processing, and healthcare domains. Extensive experiments verify the superior performance of our strategies. Our work fills the gap in benchmarks and techniques for practical imbalanced regression problems.


Delving into Deep Imbalanced Regression
Yuzhe Yang, Kaiwen Zha, Ying-Cong Chen, Hao Wang, and Dina Katabi
International Conference on Machine Learning (ICML 2021)
Long Talk (top 3%)
[Paper]  •  [Code]  •  [Blog Post]  •  [BibTeX]


Code, Data, and Models

Code, Data, and Models


(1) New Task: Deep Imbalanced Regression (DIR).

(2) New Techniques: Label distribution smoothing (LDS) & Feature distribution smoothing (FDS).

(3) New Benchmarks:


  title={Delving into Deep Imbalanced Regression},
  author={Yang, Yuzhe and Zha, Kaiwen and Chen, Ying-Cong and Wang, Hao and Katabi, Dina},
  booktitle={International Conference on Machine Learning (ICML)},

Related Publications

Rethinking the Value of Labels for Improving Class-Imbalanced Learning
Yuzhe Yang, and Zhi Xu
Conference on Neural Information Processing Systems (NeurIPS 2020)
[Project Page]  •  [Paper]  •  [Code]  •  [Talk]