High Fidelity Synthetic Face Generation for Rosacea Skin Condition from Limited Data
Not on the map. Why?
Abstract (arXiv)
Similar to the majority of deep learning applications, diagnosing skin diseases using computer vision and deep learning often requires a large volume of data. However, obtaining sufficient data for particular types of facial skin conditions can be difficult due to privacy concerns. As a result, conditions like Rosacea are often understudied in computer-aided diagnosis. The limited availability of data for facial skin conditions has led to the investigation of alternative methods for computer-aided diagnosis. In recent years, Generative Adversarial Networks (GANs), mainly variants of StyleGANs, have demonstrated promising results in generating synthetic facial images. In this study, for the first time, a small dataset of Rosacea with 300 full-face images is utilized to further investigate the possibility of generating synthetic data. The preliminary experiments show how fine-tuning the model and varying experimental settings significantly affect the fidelity of the Rosacea features. It is demonstrated that R1 Regularization strength helps achieve high-fidelity details. Additionally, this study presents qualitative evaluations of synthetic/generated faces by expert dermatologists and non-specialist participants. The quantitative evaluation is presented using a few validation metric(s). Furthermore a number of limitations and future directions are discussed. Code and generated dataset are available at: urlhttps://github.com/thinkercache/stylegan2-ada-pytorch
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 32 of its 68 references that are in the map. First posted on arXiv 8 Mar 2023.
Builds on
32 of 68 references.
References · 32
- 2020Denoising Diffusion Probabilistic Modelscited by 20,851
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
- 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
- 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
- 2022Generative Adversarial Networkscited by 5,603
- 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
- 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
- 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
- 2016Improved Techniques for Training GANscited by 2,938
- 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
- 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
- 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
20 more
- 2018Demystifying MMD GANscited by 1,268
- 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
- 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,176
- 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 925
- 2018Which Training Methods for GANs do actually Converge?cited by 672
- 2017Are GANs Created Equal? A Large-Scale Studycited by 267
- 2020A Review on Generative Adversarial Networks: Algorithms, Theory, and Applicationscited by 209
- 2020Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANscited by 132
- 2021Pros and Cons of GAN Evaluation Measures: New Developmentscited by 121
- 2017Stabilizing Training of Generative Adversarial Networks through Regularizationcited by 118
- 2019A deep learning system for differential diagnosis of skin diseasescited by 118
- 2017The Numerics of GANscited by 104
- 2020Image Augmentations for GAN Trainingcited by 78
- 2020Improved Consistency Regularization for GANscited by 67
- 2017Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Stepcited by 45
- 2019DermGAN: Synthetic Generation of Clinical Skin Images with Pathologycited by 33
- 2021GAN-Based Data Augmentation and Anonymization for Skin-Lesion Analysis: A Critical Reviewcited by 25
- 2019Skin Lesion Synthesis with Generative Adversarial Networkscited by 22
- 2018MelanoGANs: High Resolution Skin Lesion Synthesis with GANscited by 14
- 2019Learning Neural Networks with Adaptive Regularizationcited by 5
Built on by
Citing papers per year: 2024: 1.
1 paper.