Delving into Deep Imbalanced Regression

02/18/2021
by   Yuzhe Yang, et al.
17

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. Code and data are available at https://github.com/YyzHarry/imbalanced-regression.

READ FULL TEXT

page 4

page 8

page 20

page 22

research
09/13/2023

ConR: Contrastive Regularizer for Deep Imbalanced Regression

Imbalanced distributions are ubiquitous in real-world data. They create ...
research
06/11/2023

Variational Imbalanced Regression

Existing regression models tend to fall short in both accuracy and uncer...
research
09/14/2021

Variation-Incentive Loss Re-weighting for Regression Analysis on Biased Data

Both classification and regression tasks are susceptible to the biased d...
research
06/04/2022

Interpretable Models Capable of Handling Systematic Missingness in Imbalanced Classes and Heterogeneous Datasets

Application of interpretable machine learning techniques on medical data...
research
05/30/2022

RankSim: Ranking Similarity Regularization for Deep Imbalanced Regression

Data imbalance, in which a plurality of the data samples come from a sma...
research
03/17/2022

On Multi-Domain Long-Tailed Recognition, Generalization and Beyond

Real-world data often exhibit imbalanced label distributions. Existing s...
research
03/30/2021

Continuous Weight Balancing

We propose a simple method by which to choose sample weights for problem...

Please sign up or login with your details

Forgot password? Click here to reset