Distributional Loss for Robust Classification

2026-06-11

AI Summary

This work addresses the limitations of conventional classification losses, which are prone to overfitting and exhibit poor robustness in scenarios involving ambiguous class boundaries or limited training samples. To this end, the authors propose a novel distributional loss function that models classification outputs as bimodal Gaussian distributions, thereby implicitly capturing class uncertainty and softening decision boundaries. This approach uniquely relaxes the classification target into a bimodal distribution without requiring additional annotations, necessitating only minimal modifications to standard training pipelines. End-to-end optimization is achieved through distribution matching. Extensive experiments demonstrate that the proposed method significantly enhances model robustness across multiple benchmark datasets, with particularly pronounced gains in low-data regimes.

Abstract

This paper proposes a novel loss concept for supervised classification tasks. Rather than enforcing a direct mapping from each input sample to a single assigned label, we define an optimization objective over all classifier outputs as a bimodal Gaussian distribution. This softer target formulation implicitly captures class ambiguity, mitigates overfitting, and encourages the learning of more robust decision boundaries, all without requiring additional label information. Experimental results demonstrate consistent improvements in robustness, with particularly pronounced gains in low-data regimes, while requiring only minimal modifications to standard training pipelines.

Problem

• supervised classification
• class ambiguity
• overfitting
• low-data regimes
• robustness

Innovation

• distributional loss
• bimodal Gaussian
• robust classification
• class ambiguity
• low-data regime