VB-Mitigator: An Open-source Framework for Evaluating and Advancing Visual Bias Mitigation
Not on the map. Why?
Abstract (arXiv)
Bias in computer vision models remains a significant challenge, often resulting in unfair, unreliable, and non-generalizable AI systems. Although research into bias mitigation has intensified, progress continues to be hindered by fragmented implementations and inconsistent evaluation practices. Disparate datasets and metrics used across studies complicate reproducibility, making it difficult to fairly assess and compare the effectiveness of various approaches. To overcome these limitations, we introduce the Visual Bias Mitigator (VB-Mitigator), an open-source framework designed to streamline the development, evaluation, and comparative analysis of visual bias mitigation techniques. VB-Mitigator offers a unified research environment encompassing 12 established mitigation methods, 7 diverse benchmark datasets. A key strength of VB-Mitigator is its extensibility, allowing for seamless integration of additional methods, datasets, metrics, and models. VB-Mitigator aims to accelerate research toward fairness-aware computer vision models by serving as a foundational codebase for the research community to develop and assess their approaches. To this end, we also recommend best evaluation practices and provide a comprehensive performance comparison among state-of-the-art methodologies.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 27 of its 34 references that are in the map. First posted on arXiv 24 Jul 2025.
Builds on
27 of 34 references.
References · 27
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
- 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
- 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
- 2014Deep Learning Face Attributes in the Wildcited by 3,693
- 2020Supervised Contrastive Learningcited by 2,829
- 2019A Survey on Bias and Fairness in Machine Learningcited by 1,917
- 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,247
- 2021Just Train Twice: Improving Group Robustness without Training Group Informationcited by 523
- 2017Age Progression/Regression by Conditional Adversarial Autoencodercited by 429
- 2020Noise or Signal: The Role of Image Backgrounds in Object Recognitioncited by 343
15 more
- 2020Gradient Starvation: A Learning Proclivity in Neural Networkscited by 267
- 2019Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigationcited by 252
- 2019Learning De-biased Representations with Biased Representationscited by 199
- 2021EnD: Entangling and Disentangling deep representations for bias correctioncited by 105
- 2022A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Otherscited by 85
- 2021A Survey on Bias in Visual Datasetscited by 84
- 2022Discover and Mitigate Unknown Biases with Debiasing Alternate Networkscited by 47
- 2022Unbiased Supervised Contrastive Learningcited by 40
- 2024Second Edition FRCSyn Challenge at CVPR 2024: Face Recognition Challenge in the Era of Synthetic Datacited by 22
- 2023FLAC: Fairness-Aware Representation Learning by Suppressing Attribute-Class Associationscited by 18
- 2023Towards Fair Face Verification: An In-depth Analysis of Demographic Biasescited by 14
- 2024BAdd: Bias Mitigation through Bias Additioncited by 5
- 2024MAVias: Mitigate any Visual Biascited by 5
- 2024Say My Name: a Model's Bias Discovery Frameworkcited by 4
- 2024FaceX: Understanding Face Attribute Classifiers through Summary Model Explanationscited by 2
Built on by
Citing papers per year: 2026: 2.
2 papers.