Examining Pathological Bias in a Generative Adversarial Network Discriminator: A Case Study on a StyleGAN3 Model
Generative adversarial networks (GANs) generate photorealistic faces that are often indistinguishable by humans from real faces. While biases in machine learning models are often assumed to be due to biases in training data, we find pathological internal color and luminance biases in the discriminator of a pre-trained StyleGAN3-r model that are not explicable by the training data. We also find that the discriminator systematically stratifies scores by both image- and face-level qualities and that this disproportionately affects images across gender, race, and other categories. We examine axes common in research on stereotyping in social psychology.
Code (0)
등록된 구현이 없습니다.
Tasks
Generative Adversarial NetworkSimilar Papers 제목 키워드 기반
PGcGAN: Pathological Gait-Conditioned GAN for Human Gait Synthesis
Pathological gait analysis is constrained by limited and variable clinical datasets, which restrict the modeling of diverse gait impairments. To address this challenge, we propose a Pathological Gait-conditioned Generati…
Data AugmentationGait RecognitionBrain Status Transferring Generative Adversarial Network for Decoding Individualized Atrophy in Alzheimer’s Disease
Deep learning has been widely investigated in brain image computational analysis for diagnosing brain diseases such as Alzheimer's disease (AD). Most of the existing methods built end-to-end models to learn discriminativ…
Generative Adversarial NetworkFeature Statistics Mixing Regularization for Generative Adversarial Networks
In generative adversarial networks, improving discriminators is one of the key components for generation performance. As image classifiers are biased toward texture and debiasing improves accuracy, we investigate 1) if t…
PredictionA New GAN-based End-to-End TTS Training Algorithm
End-to-end, autoregressive model-based TTS has shown significant performance improvements over the conventional one. However, the autoregressive module training is affected by the exposure bias, or the mismatch between t…
Generative Adversarial NetworkSentenceTransfer LearningOut-of-domain Detection based on Generative Adversarial Network
The main goal of this paper is to develop out-of-domain (OOD) detection for dialog systems. We propose to use only in-domain (IND) sentences to build a generative adversarial network (GAN) of which the discriminator gene…
Generative Adversarial NetworkOut of Distribution (OOD) DetectionSentence Embedding