paper-with-me

Papers

Toward responsible face datasets: modeling the distribution of a disentangled latent space for sampling face images from demographic groups

2023-09-15 · Parsa Rahimi, Christophe Ecabert, Sebastien Marcel

Recently, it has been exposed that some modern facial recognition systems could discriminate specific demographic groups and may lead to unfair attention with respect to various facial attributes such as gender and origin. The main reason are the biases inside datasets, unbalanced demographics, used to train theses models. Unfortunately, collecting a large-scale balanced dataset with respect to various demographics is impracticable. In this paper, we investigate as an alternative the generation of a balanced and possibly bias-free synthetic dataset that could be used to train, to regularize or to evaluate deep learning-based facial recognition models. We propose to use a simple method for modeling and sampling a disentangled projection of a StyleGAN latent space to generate any combination of demographic groups (e.g. $hispanic-female$). Our experiments show that we can synthesis any combination of demographic groups effectively and the identities are different from the original training dataset. We also released the source code.

📄 PDF Abstract BibTeX arXiv:2309.08442

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
HuMan(Expedia)||How do I get a human at Expedia? How do I get a human at Expedia? How Do I Get a Human at Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Real-Time Help & Exclusive…
R1 Regularization R_INLINE_MATH_1 Regularization is a regularization technique and gradient penalty for training [generative adversarial…
Feedforward Network A Feedforward Network, or a Multilayer Perceptron (MLP), is a neural network with solely densely connected layers. This is the classic neural network architecture of the…
Adaptive Instance Normalization 설명 없음
StyleGAN 설명 없음

Similar Papers 제목 키워드 기반

Hierarchical Face Aging through Disentangled Latent Characteristics

2020-08-01 · ECCV 2020 8 · Pei-Pei Li, Huaibo Huang, Yibo Hu, Xiang Wu 외

Current age datasets lie in a long-tailed distribution, which brings difficulties to describe the aging mechanism for the imbalance ages. To alleviate it, we design a novel facial age prior to guide the aging mechanism m…

Age EstimationMORPH

Bayes-Factor-VAE: Hierarchical Bayesian Deep Auto-Encoder Models for Factor Disentanglement

2019-09-06 · ICCV 2019 10 · Minyoung Kim, Yuting Wang, Pritish Sahu, Vladimir Pavlovic

We propose a family of novel hierarchical Bayesian deep auto-encoder models capable of identifying disentangled factors of variability in data. While many recent attempts at factor disentanglement have focused on sophist…

Disentanglement

DRDM: A Disentangled Representations Diffusion Model for Synthesizing Realistic Person Images

2024-12-25 · Enbo Huang, Yuan Zhang, Faliang Huang, Guangyu Zhang 외

Person image synthesis with controllable body poses and appearances is an essential task owing to the practical needs in the context of virtual try-on, image editing and video production. However, existing methods face s…

Image GenerationPose TransferVirtual Try-on

Physically-Guided Disentangled Implicit Rendering for 3D Face Modeling

2022-01-01 · CVPR 2022 1 · Zhenyu Zhang, Yanhao Ge, Ying Tai, Weijian Cao 외

This paper presents a novel Physically-guided Disentangled Implicit Rendering (PhyDIR) framework for high-fidelity 3D face modeling. The motivation comes from two observations: widely-used graphics renderers yield ex…

3D Face ModellingNeural Rendering

Learning Disentangled Avatars with Hybrid 3D Representations

2023-09-12 · Yao Feng, Weiyang Liu, Timo Bolkart, Jinlong Yang 외

Tremendous efforts have been made to learn animatable and photorealistic human avatars. Towards this end, both explicit and implicit 3D representations are heavily studied for a holistic modeling and capture of the whole…

Disentanglement