The key objective of Generative Adversarial Networks (GANs) is to generate new data with the same statistics as the provided training data. However, multiple recent works show that state-of-the-art architectures yet struggle to achieve this goal. In particular, they report an elevated amount of high frequencies in the spectral statistics which makes it straightforward to distinguish real and generated images. Explanations for this phenomenon are controversial: While most works attribute the artifacts to the generator, other works point to the discriminator. We take a sober look at those explanations and provide insights on what makes proposed measures against high-frequency artifacts effective. To achieve this, we first independently assess the architectures of both the generator and discriminator and investigate if they exhibit a frequency bias that makes learning the distribution of high-frequency content particularly problematic. Based on these experiments, we make the following four observations: 1) Different upsampling operations bias the generator towards different spectral properties. 2) Checkerboard artifacts introduced by upsampling cannot explain the spectral discrepancies alone as the generator is able to compensate for these artifacts. 3) The discriminator does not struggle with detecting high frequencies per se but rather struggles with frequencies of low magnitude. 4) The downsampling operations in the discriminator can impair the quality of the training signal it provides. In light of these findings, we analyze proposed measures against high-frequency artifacts in state-of-the-art GAN training but find that none of the existing approaches can fully resolve spectral artifacts yet. Our results suggest that there is great potential in improving the discriminator and that this could be key to match the distribution of the training data more closely.
Are generative models fair? A study of racial bias in dermatological image generation
Instituto Universitario de Investigación en Tecnología Centrada en el Ser Humano, Universitat Politècnica de València（瓦伦西亚理工大学 以人为本技术大学研究所）；Technical University of Denmark（丹麦技术大学）
MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）；Adobe Research（Adobe 研究院）
We present a method for projecting an input image into the space of a class-conditional generative neural network. We propose a method that optimizes for transformation to counteract the model biases in generative neural networks. Specifically, we demonstrate that one can solve for image translation, scale, and global color transformation, during the projection optimization to address the object-center bias and color bias of a Generative Adversarial Network. This projection process poses a difficult optimization problem, and purely gradient-based optimizations fail to find good solutions. We d…
Advances in generative modeling based on GANs has motivated the community to find their use beyond image generation and editing tasks. In particular, several recent works have shown that GAN representations can be re-purposed for discriminative tasks such as part segmentation, especially when training data is limited. But how do these improvements stack-up against recent advances in self-supervised learning? Motivated by this we present an alternative approach based on contrastive learning and compare their performance on standard few-shot part segmentation benchmarks. Our experiments reveal t…
Datasets are crucial when training a deep neural network. When datasets are unrepresentative, trained models are prone to bias because they are unable to generalise to real world settings. This is particularly problematic for models trained in specific cultural contexts, which may not represent a wide range of races, and thus fail to generalise. This is a particular challenge for Driver drowsiness detection, where many publicly available datasets are unrepresentative as they cover only certain ethnicity groups. Traditional augmentation methods are unable to improve a model's performance when t…
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…
Generative adversarial networks (GANs) transform low-dimensional latent vectors into visually plausible images. If the real dataset contains only clean images, then ostensibly, the manifold learned by the GAN should contain only clean images. In this paper, we propose to denoise corrupted images by finding the nearest point on the GAN manifold, recovering latent vectors by minimizing distances in image space. We first demonstrate that given a corrupted version of an image that truly lies on the GAN manifold, we can approximately recover the latent vector and denoise the image, obtaining signif…
Exposing Blindspots: Cultural Bias Evaluation in Generative Image Models
Carnegie Mellon University（卡内基梅隆大学）；Dongguk University（东国大学）；Delft University of Technology（代尔夫特理工大学）；Johns Hopkins University, School of Medicine（约翰霍普金斯大学医学院）；University of Minnesota–Twin Cities（明尼苏达大学双城分校）；Lavoro AI
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）
Generative models (e.g., GANs, diffusion models) learn the underlying data distribution in an unsupervised manner. However, many applications of interest require sampling from a particular region of the output space or sampling evenly over a range of characteristics. For efficient sampling in these scenarios, we propose Generative Visual Prompt (PromptGen), a framework for distributional control over pre-trained generative models by incorporating knowledge of other off-the-shelf models. PromptGen defines control as energy-based models (EBMs) and samples images in a feed-forward manner by appro…
Bayesian generative models can flag performance loss, bias, and out-of-distribution image content
Instituto Universitario de Investigación en Tecnología Centrada en el Ser Humano, Universitat Politècnica de València（瓦伦西亚理工大学人类中心技术研究大学学院）；Technical University of Denmark（丹麦技术大学）
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）
Deep generative models seek to recover the process with which the observed data was generated. They may be used to synthesize new samples or to subsequently extract representations. Successful approaches in the domain of images are driven by several core inductive biases. However, a bias to account for the compositional way in which humans structure a visual scene in terms of objects has frequently been overlooked. In this work, we investigate object compositionality as an inductive bias for Generative Adversarial Networks (GANs). We present a minimal modification of a standard generator to in…
On the Fairness, Diversity and Reliability of Text-to-Image Generative Models
University of Western Australia（西澳大学）；University of Melbourne（墨尔本大学）；University of British Columbia（不列颠哥伦比亚大学）；Australian National University（澳大利亚国立大学）
Generative Adversarial Networks (GANs) are susceptible to bias, learned from either the unbalanced data, or through mode collapse. The networks focus on the core of the data distribution, leaving the tails - or the edges of the distribution - behind. We argue that this bias is responsible not only for fairness concerns, but that it plays a key role in the collapse of latent-traversal editing methods when deviating away from the distribution's core. Building on this observation, we outline a method for mitigating generative bias through a self-conditioning process, where distances in the latent…
University of Waterloo（滑铁卢大学）；Waterloo Artificial Intelligence Institute（滑铁卢人工智能研究所）；Lunenfeld-Tanenbaum Research Institute (LTRI)（卢嫩菲尔德-塔南鲍姆研究所（LTRI））；Sinai Health System（西奈卫生系统）；University of Toronto（多伦多大学）
Generative Adversarial Networks (GANs) have shown considerable promise for mitigating the challenge of data scarcity when building machine learning-driven analysis algorithms. Specifically, a number of studies have shown that GAN-based image synthesis for data augmentation can aid in improving classification accuracy in a number of medical image analysis tasks, such as brain and liver image analysis. However, the efficacy of leveraging GANs for tackling prostate cancer analysis has not been previously explored. Motivated by this, in this study we introduce ProstateGAN, a GAN-based model for sy…
In recent years, considerable progress has been made in the visual quality of Generative Adversarial Networks (GANs). Even so, these networks still suffer from degradation in quality for high-frequency content, stemming from a spectrally biased architecture, and similarly unfavorable loss functions. To address this issue, we present a novel general-purpose Style and WAvelet based GAN (SWAGAN) that implements progressive generation in the frequency domain. SWAGAN incorporates wavelets throughout its generator and discriminator architectures, enforcing a frequency-aware latent representation at …
Shandong University（山东大学）；City University of Hong Kong（香港城市大学）；De Montfort University（德蒙福特大学）；Peking University（北京大学）；Peng Cheng Laboratory（鹏城实验室）
We propose a generative adversarial network for point cloud upsampling, which can not only make the upsampled points evenly distributed on the underlying surface but also efficiently generate clean high frequency regions. The generator of our network includes a dynamic graph hierarchical residual aggregation unit and a hierarchical residual aggregation unit for point feature extraction and upsampling, respectively. The former extracts multiscale point-wise descriptive features, while the latter captures rich feature details with hierarchical residuals. To generate neat edges, our discriminator…
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…
Combating Pattern and Content Bias: Adversarial Feature Learning for Generalized AI-Generated Image Detection
Chongqing Key Laboratory of Image Cognition, School of Computer Science and Technology, Chongqing University of Posts and Telecommunications（重庆图像认知重点实验室，重庆邮电大学计算机科学与技术学院）；Faculty of Science and Technology of the University of Macau（澳门大学科学与技术学院）；Jinan Inspur Data Technology Co., Ltd.（济南 Inspur 数据科技有限公司）
Published studies have suggested the bias of automated face-based gender classification algorithms across gender-race groups. Specifically, unequal accuracy rates were obtained for women and dark-skinned people. To mitigate the bias of gender classifiers, the vision community has developed several strategies. However, the efficacy of these mitigation strategies is demonstrated for a limited number of races mostly, Caucasian and African-American. Further, these strategies often offer a trade-off between bias and classification accuracy. To further advance the state-of-the-art, we leverage the p…
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…
Reducing Bias and Variance: Generative Semantic Guidance and Bi-Layer Ensemble for Image Clustering
Institute of Big Data Science and Industry（大数据科学与产业研究院）；Key Laboratory of Evolutionary Science Intelligence of Shanxi Province（山西省进化智能科学重点实验室）；School of Artificial Intelligence, Shanxi University（山西大学人工智能学院）
Modern deep generative models can assign high likelihood to inputs drawn from outside the training distribution, posing threats to models in open-world deployments. While much research attention has been placed on defining new test-time measures of OOD uncertainty, these methods do not fundamentally change how deep generative models are regularized and optimized in training. In particular, generative models are shown to overly rely on the background information to estimate the likelihood. To address the issue, we propose a novel frequency-regularized learning FRL framework for OOD detection, w…
