# StyleDiff: Attribute Comparison Between Unlabeled Datasets in Latent Disentangled Space

arXiv: https://arxiv.org/abs/2303.05102 · HTML: https://mlsanity.com/paper/2303.05102/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 35 references that are in the map.
- First posted on arXiv 9 Mar 2023.

## Builds on (most cited first, 20 of 20)

- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery](https://mlsanity.com/paper/2103.17249/) (2021)
- [Computational Optimal Transport](https://mlsanity.com/paper/1803.00567/) (2018)
- [GANSpace: Discovering Interpretable GAN Controls](https://mlsanity.com/paper/2004.02546/) (2020)
- [StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation](https://mlsanity.com/paper/2011.12799/) (2020)
- [ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinement](https://mlsanity.com/paper/2104.02699/) (2021)
- [Effectively Unbiased FID and Inception Score and where to find them](https://mlsanity.com/paper/1911.07023/) (2019)
- [Geometric Dataset Distances via Optimal Transport](https://mlsanity.com/paper/2002.02923/) (2020)
- [Gromov-Wasserstein Alignment of Word Embedding Spaces](https://mlsanity.com/paper/1809.00013/) (2018)
- [Explaining in Style: Training a GAN to explain a classifier in StyleSpace](https://mlsanity.com/paper/2104.13369/) (2021)
- [Deep Active Learning: Unified and Principled Method for Query and Training](https://mlsanity.com/paper/1911.09162/) (2019)
- [Practical Coreset Constructions for Machine Learning](https://mlsanity.com/paper/1703.06476/) (2017)
- [Third Time's the Charm? Image and Video Editing with StyleGAN3](https://mlsanity.com/paper/2201.13433/) (2022)
- [Retrieve in Style: Unsupervised Facial Feature Transfer and Retrieval](https://mlsanity.com/paper/2107.06256/) (2021)
- [Partial Wasserstein Covering](https://mlsanity.com/paper/2106.00886/) (2021)

## Abstract (arXiv)

One major challenge in machine learning applications is coping with mismatches between the datasets used in the development and those obtained in real-world applications. These mismatches may lead to inaccurate predictions and errors, resulting in poor product quality and unreliable systems. In this study, we propose StyleDiff to inform developers of the differences between the two datasets for the steady development of machine learning systems. Using disentangled image spaces obtained from recently proposed generative models, StyleDiff compares the two datasets by focusing on attributes in the images and provides an easy-to-understand analysis of the differences between the datasets. The proposed StyleDiff performs in O (d Nlog N), where N is the size of the datasets and d is the number of attributes, enabling the application to large datasets. We demonstrate that StyleDiff accurately detects differences between datasets and presents them in an understandable format using, for example, driving scenes datasets.