# Unsupervised Anomaly Appraisal of Cleft Faces Using a StyleGAN2-based Model Adaptation Technique

arXiv: https://arxiv.org/abs/2211.06659 · HTML: https://mlsanity.com/paper/2211.06659/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 80 references that are in the map.
- First posted on arXiv 12 Nov 2022.

## Builds on (most cited first, 21 of 21)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size](https://mlsanity.com/paper/1602.07360/) (2016)
- [Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?](https://mlsanity.com/paper/1904.03189/) (2019)
- [Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery](https://mlsanity.com/paper/1703.05921/) (2017)
- [In-Domain GAN Inversion for Real Image Editing](https://mlsanity.com/paper/2004.00049/) (2020)
- [Image2StyleGAN++: How to Edit the Embedded Images?](https://mlsanity.com/paper/1911.11544/) (2019)
- [CIPS-3D: A 3D-Aware Generator of GANs Based on Conditionally-Independent Pixel Synthesis](https://mlsanity.com/paper/2110.09788/) (2021)
- [Transferring GANs: generating images from limited data](https://mlsanity.com/paper/1805.01677/) (2018)
- [Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANs](https://mlsanity.com/paper/2002.10964/) (2020)
- [Invertible Conditional GANs for image editing](https://mlsanity.com/paper/1611.06355/) (2016)
- [Image Generation From Small Datasets via Batch Statistics Adaptation](https://mlsanity.com/paper/1904.01774/) (2019)
- [COCO-GAN: Generation by Parts via Conditional Coordinating](https://mlsanity.com/paper/1904.00284/) (2019)
- [Collaborative Learning for Faster StyleGAN Embedding](https://mlsanity.com/paper/2007.01758/) (2020)
- [Improved Transformer for High-Resolution GANs](https://mlsanity.com/paper/2106.07631/) (2021)
- [DOPING: Generative Data Augmentation for Unsupervised Anomaly Detection with GAN](https://mlsanity.com/paper/1808.07632/) (2018)
- [Identifying and Categorizing Anomalies in Retinal Imaging Data](https://mlsanity.com/paper/1612.00686/) (2016)
- [Learning Inverse Mapping by Autoencoder based Generative Adversarial Nets](https://mlsanity.com/paper/1703.10094/) (2017)

## Built on by (most cited first, 1 of 1)

- [CleftGAN: Adapting A Style-Based Generative Adversarial Network To Create Images Depicting Cleft Lip Deformity](https://mlsanity.com/paper/2310.07969/) (2023)

## Abstract (arXiv)

This paper presents a novel machine learning framework to consistently detect, localize and rate congenital cleft lip anomalies in human faces. The goal is to provide a universal, objective measure of facial differences and reconstructive surgical outcomes that matches human judgments. The proposed method employs the StyleGAN2 generative adversarial network with model adaptation to produce normalized transformations of cleft-affected faces in order to allow for subsequent measurement of deformity using a pixel-wise subtraction approach. The complete pipeline of the proposed framework consists of the following steps: image preprocessing, face normalization, color transformation, morphological erosion, heat-map generation and abnormality scoring. Heatmaps that finely discern anatomic anomalies are proposed by exploiting the features of the considered framework. The proposed framework is validated through computer simulations and surveys containing human ratings. The anomaly scores yielded by the proposed computer model correlate closely with the human ratings of facial differences, leading to 0.942 Pearson's r score.