Targeted Data Augmentation for bias mitigation
The development of fair and ethical AI systems requires careful consideration of bias mitigation, an area often overlooked or ignored. In this study, we introduce a novel and efficient approach for addressing biases called Targeted Data Augmentation (TDA), which leverages classical data augmentation techniques to tackle the pressing issue of bias in data and models. Unlike the laborious task of removing biases, our method proposes to insert biases instead, resulting in improved performance. To identify biases, we annotated two diverse datasets: a dataset of clinical skin lesions and a dataset of male and female faces. These bias annotations are published for the first time in this study, providing a valuable resource for future research. Through Counterfactual Bias Insertion, we discovered that biases associated with the frame, ruler, and glasses had a significant impact on models. By randomly introducing biases during training, we mitigated these biases and achieved a substantial decrease in bias measures, ranging from two-fold to more than 50-fold, while maintaining a negligible increase in the error rate.
Code (0)
등록된 구현이 없습니다.
Tasks
counterfactualData AugmentationSimilar Papers 제목 키워드 기반
No Free Lunch in Language Model Bias Mitigation? Targeted Bias Reduction Can Exacerbate Unmitigated LLM Biases
Large Language Models (LLMs) inherit societal biases from their training data, potentially leading to harmful or unfair outputs. While various techniques aim to mitigate these biases, their effects are often evaluated on…
Freeze and Reveal: Exposing Modality Bias in Vision-Language Models
Vision Language Models achieve impressive multi-modal performance but often inherit gender biases from their training data. This bias might be coming from both the vision and text modalities. In this work, we dissect the…
Data AugmentationData augmentation and explainability for bias discovery and mitigation in deep learning
This dissertation explores the impact of bias in deep neural networks and presents methods for reducing its influence on model performance. The first part begins by categorizing and describing potential sources of bias a…
Data AugmentationStyle TransferEfficient Bias Mitigation Without Privileged Information
Deep neural networks trained via empirical risk minimisation often exhibit significant performance disparities across groups, particularly when group and task labels are spuriously correlated (e.g., "grassy background" a…
Model SelectionPreventing Shortcut Learning in Medical Image Analysis through Intermediate Layer Knowledge Distillation from Specialist Teachers
Deep learning models are prone to learning shortcut solutions to problems using spuriously correlated yet irrelevant features of their training data. In high-risk applications such as medical image analysis, this phenome…
Knowledge Distillation