It is tempting to think that machines are less prone to unfairness and prejudice. However, machine learning approaches compute their outputs based on data. While biases can enter at any stage of the development pipeline, models are particularly receptive to mirror biases of the datasets they are trained on and therefore do not necessarily reflect truths about the world but, primarily, truths about the data. To raise awareness about the relationship between modern algorithms and the data that shape them, we use a conditional invertible neural network to disentangle the dataset-specific information from the information which is shared across different datasets. In this way, we can project the same image onto different datasets, thereby revealing their inherent biases. We use this methodology to (i) investigate the impact of dataset quality on the performance of generative models, (ii) show how societal biases of datasets are replicated by generative models, and (iii) present creative applications through unpaired transfer between diverse datasets such as photographs, oil portraits, and animes. Our code and an interactive demonstration are available at https://github.com/CompVis/net2net .
Models that are learned from real-world data are often biased because the data used to train them is biased. This can propagate systemic human biases that exist and ultimately lead to inequitable treatment of people, especially minorities. To characterize bias in learned classifiers, existing approaches rely on human oracles labeling real-world examples to identify the "blind spots" of the classifiers; these are ultimately limited due to the human labor required and the finite nature of existing image examples. We propose a simulation-based approach for interrogating classifiers using generati…
TIBET: Identifying and Evaluating Biases in Text-to-Image Generative Models
University of British Columbia（不列颠哥伦比亚大学）；Vector Institute for AI（Vector人工智能研究院）；Toyota Technological Institute at Chicago（芝加哥丰田理工学院）；Carleton College（卡尔顿学院）；University of Pennsylvania（宾夕法尼亚大学）
An open secret in contemporary machine learning is that many models work beautifully on standard benchmarks but fail to generalize outside the lab. This has been attributed to biased training data, which provide poor coverage over real world events. Generative models are no exception, but recent advances in generative adversarial networks (GANs) suggest otherwise - these models can now synthesize strikingly realistic and diverse images. Is generative modeling of photos a solved problem? We show that although current GANs can fit standard datasets very well, they still fall short of being compr…
Real-world datasets are often biased with respect to key demographic factors such as race and gender. Due to the latent nature of the underlying factors, detecting and mitigating bias is especially challenging for unsupervised machine learning. We present a weakly supervised algorithm for overcoming dataset bias for deep generative models. Our approach requires access to an additional small, unlabeled reference dataset as the supervision signal, thus sidestepping the need for explicit labels on the underlying bias factors. Using this supplementary dataset, we detect the bias in existing datase…
A Large Scale Analysis of Gender Biases in Text-to-Image Generative Models
Technical University of Munich, Munich Center for Machine Learning, MDSI（慕尼黑技术大学、慕尼黑机器学习中心、MDSI）；LTCI, Télécom Paris, Institut Polytechnique de Paris（LTCI、巴黎电信学院、巴黎理工学院）；Helmholtz Munich（海德堡-慕尼黑研究中心）；University of California, Berkeley（加州大学伯克利分校）
Dataset bias is a well-known problem in the field of computer vision. The presence of implicit bias in any image collection hinders a model trained and validated on a particular dataset to yield similar accuracies when tested on other datasets. In this paper, we propose a novel debiasing technique to reduce the effects of a biased training dataset. Our goal is to augment the training data using a generative network by learning a non-linear mapping from the source domain (training set) to the target domain (testing set) while retaining training set labels. The cycle consistency loss and adversa…
Deep Learning systems need large data for training. Datasets for training face verification systems are difficult to obtain and prone to privacy issues. Synthetic data generated by generative models such as GANs can be a good alternative. However, we show that data generated from GANs are prone to bias and fairness issues. Specifically, GANs trained on FFHQ dataset show biased behavior towards generating white faces in the age group of 20-29. We also demonstrate that synthetic faces cause disparate impact, specifically for race attribute, when used for fine tuning face verification systems.
Sun Yat-Sen University（中山大学）；The Chinese University of Hong Kong（香港中文大学）
Generative Adversarial Networks (GANs) advance face synthesis through learning the underlying distribution of observed data. Despite the high-quality generated faces, some minority groups can be rarely generated from the trained models due to a biased image generation process. To study the issue, we first conduct an empirical study on a pre-trained face synthesis model. We observe that after training the GAN model not only carries the biases in the training data but also amplifies them to some degree in the image generation process. To further improve the fairness of image generation, we propo…
The task of Visual Question Answering (VQA) is known to be plagued by the issue of VQA models exploiting biases within the dataset to make its final prediction. Various previous ensemble based debiasing methods have been proposed where an additional model is purposefully trained to be biased in order to train a robust target model. However, these methods compute the bias for a model simply from the label statistics of the training data or from single modal branches. In this work, in order to better learn the bias a target VQA model suffers from, we propose a generative method to train the bias…
Fair Diffusion: Instructing Text-to-Image Generation Models on Fairness
Technical University of Darmstadt（达姆施塔特工业大学）；Hessian Center for Artificial Intelligence (hessian.AI)（黑森人工智能中心（hessian.AI））；German Center for Artificial Intelligence (DFKI)（德国人工智能研究中心（DFKI））；LAION；Huggingface（Hugging Face）
Deep learning (DL) models are widely used to provide a more convenient and smarter life. However, biased algorithms will negatively influence us. For instance, groups targeted by biased algorithms will feel unfairly treated and even fearful of negative consequences of these biases. This work targets biased generative models' behaviors, identifying the cause of the biases and eliminating them. We can (as expected) conclude that biased data causes biased predictions of face frontalization models. Varying the proportions of male and female faces in the training data can have a substantial effect …
MeDi: Metadata-Guided Diffusion Models for Mitigating Biases in Tumor Classification
Machine Learning Group, Technische Universität Berlin, Germany The Konrad Zuse School of Excellence in Learning；Intelligent Systems (ELIZA), Germany BIFOLD – Berlin Institute for the Foundations of Learning
Arizona State University（亚利桑那州立大学）；Rensselaer Polytechnic Institute（伦斯勒理工学院）
In this paper, we show that popular Generative Adversarial Networks (GANs) exacerbate biases along the axes of gender and skin tone when given a skewed distribution of face-shots. While practitioners celebrate synthetic data generation using GANs as an economical way to augment data for training data-hungry machine learning models, it is unclear whether they recognize the perils of such techniques when applied to real world datasets biased along latent dimensions. Specifically, we show that (1) traditional GANs further skew the distribution of a dataset consisting of engineering faculty headsh…
