ASRL:A robust loss function with potential for development

2025/04/09 by Anran Zhang, Hui, Chenyu, Xintong Li +2
Computer Science · #FOS: Computer and information sciences #Face and Expression Recognition #Imbalanced Data Classification Techniques #Machine Learning (cs.LG) #Machine Learning and Data Classification

paper · pdf · doi:10.48550/arxiv.2504.06935

openalex publication_date 2025/04/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

In this article, we proposed a partition:wise robust loss function based on the previous robust loss function. The characteristics of this loss function are that it achieves high robustness and a wide range of applicability through partition-wise design and adaptive parameter adjustment. Finally, the advantages and development potential of this loss function were verified by applying this loss function to the regression question and using five different datasets (with different dimensions, different sample numbers, and different fields) to compare with the other loss functions. The results of multiple experiments have proven the advantages of our loss function .

Citations

• Fast and Accurate Road Crack Detection Based on Adaptive Cost-Sensitive Loss Function
• GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks
• Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
• Fast R-CNN

Related

• An Analysis of Loss Functions for Binary Classification and Regression
• A survey and taxonomy of loss functions in machine learning
• Penalized regression with multiple loss functions and selection by vote
• Joint Asymmetric Loss for Learning with Noisy Labels
• Kernel based regression with robust loss function via iteratively reweighted least squares