paper-with-me

Papers

ChildGAN: Large Scale Synthetic Child Facial Data Using Domain Adaptation in StyleGAN

2023-07-25 · Muhammad Ali Farooq, Wang Yao, Gabriel Costache, Peter Corcoran

In this research work, we proposed a novel ChildGAN, a pair of GAN networks for generating synthetic boys and girls facial data derived from StyleGAN2. ChildGAN is built by performing smooth domain transfer using transfer learning. It provides photo-realistic, high-quality data samples. A large-scale dataset is rendered with a variety of smart facial transformations: facial expressions, age progression, eye blink effects, head pose, skin and hair color variations, and variable lighting conditions. The dataset comprises more than 300k distinct data samples. Further, the uniqueness and characteristics of the rendered facial features are validated by running different computer vision application tests which include CNN-based child gender classifier, face localization and facial landmarks detection test, identity similarity evaluation using ArcFace, and lastly running eye detection and eye aspect ratio tests. The results demonstrate that synthetic child facial data of high quality offers an alternative to the cost and complexity of collecting a large-scale dataset from real children.

📄 PDF Abstract BibTeX arXiv:2307.13746

Code (0)

등록된 구현이 없습니다.

Tasks

Domain AdaptationTransfer Learning

Methods 이 논문이 사용한 방법론

R1 Regularization R_INLINE_MATH_1 Regularization is a regularization technique and gradient penalty for training [generative adversarial…
Path Length Regularization 설명 없음
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…
Weight Demodulation 설명 없음
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…
ArcFace ArcFace, or Additive Angular Margin Loss, is a loss function used in face recognition tasks. The softmax is traditionally used…

Similar Papers 제목 키워드 기반

Heredity-aware Child Face Image Generation with Latent Space Disentanglement

2021-08-25 · Xiao Cui, Wengang Zhou, Yang Hu, Weilun Wang 외

Generative adversarial networks have been widely used in image synthesis in recent years and the quality of the generated image has been greatly improved. However, the flexibility to control and decouple facial attribute…

DisentanglementImage Generation

ChildDiffusion: Unlocking the Potential of Generative AI and Controllable Augmentations for Child Facial Data using Stable Diffusion and Large Language Models

2024-06-17 · Muhammad Ali Farooq, Wang Yao, Peter Corcoran

In this research work we have proposed high-level ChildDiffusion framework capable of generating photorealistic child facial samples and further embedding several intelligent augmentations on child facial data using shor…

Synthetic Speaking Children -- Why We Need Them and How to Make Them

2023-11-08 · Muhammad Ali Farooq, Dan Bigioi, Rishabh Jain, Wang Yao 외

Contemporary Human Computer Interaction (HCI) research relies primarily on neural network models for machine vision and speech understanding of a system user. Such models require extensively annotated training datasets f…

text-to-speechText to Speech

Child Face Recognition at Scale: Synthetic Data Generation and Performance Benchmark

2023-04-23 · Magnus Falkenberg, Anders Bensen Ottsen, Mathias Ibsen, Christian Rathgeb

We address the need for a large-scale database of children's faces by using generative adversarial networks (GANs) and face age progression (FAP) models to synthesize a realistic dataset referred to as HDA-SynChildFaces.…

Face RecognitionSynthetic Data Generation

Synthetic Data Alone is Enough? Rethinking Data Scarcity in Pediatric Rare Disease Recognition

2026-05-21 · Ganlin Feng, Yuxi Long, Erin Lou, Lianghong Chen 외 arxiv

Children with rare genetic diseases often exhibit distinctive facial phenotypes, yet developing computer vision systems for early diagnosis remains challenging due to extreme data scarcity, privacy constraints, and limit…