# BOOST: Out-of-Distribution-Informed Adaptive Sampling for Bias Mitigation in Stylistic Convolutional Neural Networks

arXiv: https://arxiv.org/abs/2507.07134 · HTML: https://mlsanity.com/paper/2507.07134/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 36 references that are in the map.
- First posted on arXiv 8 Jul 2025.

## Builds on (most cited first, 15 of 15)

- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks](https://mlsanity.com/paper/1706.02690/) (2017)
- [Open-Set Recognition: a Good Closed-Set Classifier is All You Need?](https://mlsanity.com/paper/2110.06207/) (2021)
- [Cut and Learn for Unsupervised Object Detection and Instance Segmentation](https://mlsanity.com/paper/2301.11320/) (2023)
- [Conditional Negative Sampling for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2010.02037/) (2020)
- [Weakly Supervised Object Detection in Artworks](https://mlsanity.com/paper/1810.02569/) (2018)
- [Detecting People in Artwork with CNNs](https://mlsanity.com/paper/1610.08871/) (2016)
- [Class-Difficulty Based Methods for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2207.14499/) (2022)
- [Learned feature representations are biased by complexity, learning order, position, and more](https://mlsanity.com/paper/2405.05847/) (2024)
- [Self-supervise, Refine, Repeat: Improving Unsupervised Anomaly Detection](https://mlsanity.com/paper/2106.06115/) (2021)
- [Enhancing Human Pose Estimation in Ancient Vase Paintings via Perceptually-grounded Style Transfer Learning](https://mlsanity.com/paper/2012.05616/) (2020)
- [Practical Evaluation of Out-of-Distribution Detection Methods for Image Classification](https://mlsanity.com/paper/2101.02447/) (2021)
- [GRIT-VLP: Grouped Mini-batch Sampling for Efficient Vision and Language Pre-training](https://mlsanity.com/paper/2208.04060/) (2022)
- [Tackling Data Bias in Painting Classification with Style Transfer](https://mlsanity.com/paper/2301.02524/) (2023)
- [Bridging In- and Out-of-distribution Samples for Their Better Discriminability](https://mlsanity.com/paper/2101.02500/) (2021)

## Abstract (arXiv)

The pervasive issue of bias in AI presents a significant challenge to painting classification, and is getting more serious as these systems become increasingly integrated into tasks like art curation and restoration. Biases, often arising from imbalanced datasets where certain artistic styles dominate, compromise the fairness and accuracy of model predictions, i.e., classifiers are less accurate on rarely seen paintings. While prior research has made strides in improving classification performance, it has largely overlooked the critical need to address these underlying biases, that is, when dealing with out-of-distribution (OOD) data. Our insight highlights the necessity of a more robust approach to bias mitigation in AI models for art classification on biased training data. We propose a novel OOD-informed model bias adaptive sampling method called BOOST (Bias-Oriented OOD Sampling and Tuning). It addresses these challenges by dynamically adjusting temperature scaling and sampling probabilities, thereby promoting a more equitable representation of all classes. We evaluate our proposed approach to the KaoKore and PACS datasets, focusing on the model's ability to reduce class-wise bias. We further propose a new metric, Same-Dataset OOD Detection Score (SODC), designed to assess class-wise separation and per-class bias reduction. Our method demonstrates the ability to balance high performance with fairness, making it a robust solution for unbiasing AI models in the art domain.