Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2509.11588 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916949661843456 |
|---|---|
| author | Felske, Mirco Stiene, Stefan |
| author_facet | Felske, Mirco Stiene, Stefan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_11588 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Optimizing Class Distributions for Bias-Aware Multi-Class Learning Felske, Mirco Stiene, Stefan Computer Vision and Pattern Recognition 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. |
| title | Optimizing Class Distributions for Bias-Aware Multi-Class Learning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.11588 |