ConR: Contrastive Regularizer for Deep Imbalanced Regression
This addresses deep imbalanced regression, a domain-specific problem for machine learning practitioners dealing with continuous data, offering a generic and efficient solution that integrates with existing approaches.
The paper tackles the problem of imbalanced distributions in regression tasks, where existing methods for categorical labels fail due to continuous label spaces, and proposes ConR, a contrastive regularizer that models global and local label similarities to prevent feature collapse of minority samples, significantly boosting state-of-the-art methods on four large-scale benchmarks.
Imbalanced distributions are ubiquitous in real-world data. They create constraints on Deep Neural Networks to represent the minority labels and avoid bias towards majority labels. The extensive body of imbalanced approaches address categorical label spaces but fail to effectively extend to regression problems where the label space is continuous. Local and global correlations among continuous labels provide valuable insights towards effectively modelling relationships in feature space. In this work, we propose ConR, a contrastive regularizer that models global and local label similarities in feature space and prevents the features of minority samples from being collapsed into their majority neighbours. ConR discerns the disagreements between the label space and feature space and imposes a penalty on these disagreements. ConR addresses the continuous nature of label space with two main strategies in a contrastive manner: incorrect proximities are penalized proportionate to the label similarities and the correct ones are encouraged to model local similarities. ConR consolidates essential considerations into a generic, easy-to-integrate, and efficient method that effectively addresses deep imbalanced regression. Moreover, ConR is orthogonal to existing approaches and smoothly extends to uni- and multi-dimensional label spaces. Our comprehensive experiments show that ConR significantly boosts the performance of all the state-of-the-art methods on four large-scale deep imbalanced regression benchmarks. Our code is publicly available in https://github.com/BorealisAI/ConR.