With the recent growth in computer vision applications, the question of how fair and unbiased they are has yet to be explored. There is abundant evidence that the bias present in training data is reflected in the models, or even amplified. Many previous methods for image dataset de-biasing, including models based on augmenting datasets, are computationally expensive to implement. In this study, we present a fast and effective model to de-bias an image dataset through reconstruction and minimizing the statistical dependence between intended variables. Our architecture includes a U-net to reconstruct images, combined with a pre-trained classifier which penalizes the statistical dependence between target attribute and the protected attribute. We evaluate our proposed model on CelebA dataset, compare the results with a state-of-the-art de-biasing method, and show that the model achieves a promising fairness-accuracy combination.
FairAdaBN: Mitigating unfairness with adaptive batch normalization and its application to dermatological disease classification
Suzhou Institute for Advanced Research, University of Science and Technology of China（中国科学技术大学苏州高等研究院）；School of Biomedical Engineering, Division of Life Sciences and Medicine, University of Science and Technology of China（中国科学技术大学生命科学与医学部生物医学工程学院）
Bogazici University（博阿齐奇大学）；University of Cambridge（剑桥大学）；Beijing University of Posts and Telecommunications（北京邮电大学）
As affective robots become integral in human life, these agents must be able to fairly evaluate human affective expressions without discriminating against specific demographic groups. Identifying bias in Machine Learning (ML) systems as a critical problem, different approaches have been proposed to mitigate such biases in the models both at data and algorithmic levels. In this work, we propose Continual Learning (CL) as an effective strategy to enhance fairness in Facial Expression Recognition (FER) systems, guarding against biases arising from imbalances in data distributions. We compare diff…
University of Cambridge（剑桥大学）；Binghamton University（宾汉姆顿大学）；Beijing University of Posts and Telecommunications（北京邮电大学）
As Facial Expression Recognition (FER) systems become integrated into our daily lives, these systems need to prioritise making fair decisions instead of aiming at higher individual accuracy scores. Ranging from surveillance systems to diagnosing mental and emotional health conditions of individuals, these systems need to balance the accuracy vs fairness trade-off to make decisions that do not unjustly discriminate against specific under-represented demographic groups. Identifying bias as a critical problem in facial analysis systems, different methods have been proposed that aim to mitigate bi…
As machine learning methods are deployed in real-world settings such as healthcare, legal systems, and social science, it is crucial to recognize how they shape social biases and stereotypes in these sensitive decision-making processes. Among such real-world deployments are large-scale pretrained language models (LMs) that can be potentially dangerous in manifesting undesirable representational biases - harmful biases resulting from stereotyping that propagate negative generalizations involving gender, race, religion, and other social constructs. As a step towards improving the fairness of LMs…
Texas State University（德克萨斯州立大学）；Illinois Institute of Technology（伊利诺伊理工学院）
In recent years the ubiquitous deployment of AI has posed great concerns in regards to algorithmic bias, discrimination, and fairness. Compared to traditional forms of bias or discrimination caused by humans, algorithmic bias generated by AI is more abstract and unintuitive therefore more difficult to explain and mitigate. A clear gap exists in the current literature on evaluating and mitigating bias in pruned neural networks. In this work, we strive to tackle the challenging issues of evaluating, mitigating, and explaining induced bias in pruned neural networks. Our paper makes three contribu…
Mitigating Group-Level Fairness Disparities in Federated Visual Language Models
Great Bay University（大湾大学）；Tsinghua Shenzhen International Graduate School（清华大学深圳国际研究生院）；Nanyang Technological University（南洋理工大学）；Beijing University of Posts and Telecommunications（北京邮电大学）；Shenzhen University（深圳大学）；Pengcheng Laboratory（鹏城实验室）；Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区）
As transformer architectures become increasingly prevalent in computer vision, it is critical to understand their fairness implications. We perform the first study of the fairness of transformers applied to computer vision and benchmark several bias mitigation approaches from prior work. We visualize the feature space of the transformer self-attention modules and discover that a significant portion of the bias is encoded in the query matrix. With this knowledge, we propose TADeT, a targeted alignment strategy for debiasing transformers that aims to discover and remove bias primarily from query…
Internet search affects people's cognition of the world, so mitigating biases in search results and learning fair models is imperative for social good. We study a unique gender bias in image search in this work: the search images are often gender-imbalanced for gender-neutral natural language queries. We diagnose two typical image search models, the specialized model trained on in-domain datasets and the generalized representation model pre-trained on massive image and text data across the internet. Both models suffer from severe gender bias. Therefore, we introduce two novel debiasing approac…
Exposing and Mitigating Calibration Biases and Demographic Unfairness in MLLM Few-Shot In-Context Learning for Medical Image Classification
Centre for Intelligent Machines, McGill University, Montreal, Canada（智能机器中心，麦吉尔大学，加拿大）；Mila -- Quebec AI Institute, Montreal, Canada（魁北克人工智能研究所）；Stanford University, Stanford, USA（斯坦福大学）；University of Copenhagen, Copenhagen, Denmark（哥本哈根大学）
debiaSAE: Benchmarking and Mitigating Vision-Language Model Bias
Johns Hopkins University（约翰斯·霍普金斯大学）；University of Alabama at Birmingham（阿拉巴马大学伯明翰分校）；Harvard Medical School（哈佛医学院）；Mass General Brigham（麻省总医院布里格姆医疗系统）；Boston Children’s Hospital（波士顿儿童医院）
Convolutional Neural Networks have demonstrated human-level performance in the classification of melanoma and other skin lesions, but evident performance disparities between differing skin tones should be addressed before widespread deployment. In this work, we propose an efficient yet effective algorithm for automatically labelling the skin tone of lesion images, and use this to annotate the benchmark ISIC dataset. We subsequently use these automated labels as the target for two leading bias unlearning techniques towards mitigating skin tone bias. Our experimental results provide evidence tha…
