Optimizing Class Distributions for Bias-Aware Multi-Class Learning

Mirco Felske, Stefan Stiene
9/15/2025
cs.CV

No confident code implementation found for this paper. 2 possible matches can be shown below.

Abstract

We propose BiCDO (Bias-Controlled Class Distribution Optimizer), an iterative, data-centric framework that identifies Pareto optimized class distributions for multi-class image classification. BiCDO enables performance prioritization for specific classes, which is useful in safety-critical scenarios (e.g. prioritizing 'Human' over 'Dog'). Unlike uniform distributions, BiCDO determines the optimal number of images per class to enhance reliability and minimize bias and variance in the objective function. BiCDO can be incorporated into existing training pipelines with minimal code changes and supports any labelled multi-class dataset. We have validated BiCDO using EfficientNet, ResNet and ConvNeXt on CIFAR-10 and iNaturalist21 datasets, demonstrating improved, balanced model performance through optimized data distribution.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 2 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Few-Class Arena: A Benchmark for Efficient Selection of Vision Models and Dataset Difficulty Measurement

83% match2 repos62026

Low Saturation Confidence Distribution-based Test-Time Adaptation for Cross-Domain Remote Sensing Image Classification

82% match2024

Advancing Image Classification with Discrete Diffusion Classification Modeling

81% match1 repo232025

Investigation of Federated Learning Algorithms for Retinal Optical Coherence Tomography Image Classification with Statistical Heterogeneity

80% match1 repo22024

Iterative Online Image Synthesis via Diffusion Model for Imbalanced Classification

80% match1 repo42024

Leveraging Human-Machine Interactions for Computer Vision Dataset Quality Enhancement

80% match1 repo2024

Cite this paper

@article{felske2025optimizing,
  title  = {Optimizing Class Distributions for Bias-Aware Multi-Class Learning},
  author = {Mirco Felske and Stefan Stiene},
  year   = {2025},
  eprint = {2509.11588},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2509.11588v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2509.11588.svg)](https://codeofpaper.com/paper/2509.11588)

Discussion