Sampling Strategies for Mitigating Bias in Face Synthesis Methods
원문 초록
Synthetically generated images can be used to create media content or to complement datasets for training image analysis models. Several methods have recently been proposed for the synthesis of high-fidelity face images; however, the potential biases introduced by such methods have not been sufficiently addressed. This paper examines the bias introduced by the widely popular StyleGAN2 generative model trained on the Flickr Faces HQ dataset and proposes two sampling strategies to balance the representation of selected attributes in the generated face images. We focus on two protected attributes, gender and age, and reveal that biases arise in the distribution of randomly sampled images against very young and very old age groups, as well as against female faces. These biases are also assessed for different image quality levels based on the GIQA score. To mitigate bias, we propose two alternative methods for sampling on selected lines or spheres of the latent space to increase the number of generated samples from the under-represented classes. The experimental results show a decrease in bias against underrepresented groups and a more uniform distribution of the protected features at different levels of image quality.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
FLUXSynID: A Framework for Identity-Controlled Synthetic Face Generation with Document and Live Images
MagicPortrait: Temporally Consistent Face Reenactment with 3D Geometric Guidance
ID-Booth: Identity-consistent Face Generation with Diffusion Models
FFaceNeRF: Few-shot Face Editing in Neural Radiance Fields
JoyGen: Audio-Driven 3D Depth-Aware Talking-Face Video Editing
DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis
토론
이 논문과 연결된 포럼 글이 아직 없습니다.