# ALADIN-NST: Self-supervised disentangled representation learning of artistic style through Neural Style Transfer

arXiv: https://arxiv.org/abs/2304.05755 · HTML: https://mlsanity.com/paper/2304.05755/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 27 references that are in the map.
- First posted on arXiv 12 Apr 2023.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Multimodal Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1804.04732/) (2018)
- [Universal Style Transfer via Feature Transforms](https://mlsanity.com/paper/1705.08086/) (2017)
- [Swapping Autoencoder for Deep Image Manipulation](https://mlsanity.com/paper/2007.00653/) (2020)
- [Arbitrary Style Transfer with Style-Attentional Networks](https://mlsanity.com/paper/1812.02342/) (2018)
- [Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks](https://mlsanity.com/paper/1604.04382/) (2016)
- [Texture Networks: Feed-forward Synthesis of Textures and Stylized Images](https://mlsanity.com/paper/1603.03417/) (2016)
- [Avatar-Net: Multi-scale Zero-shot Style Transfer by Feature Decoration](https://mlsanity.com/paper/1805.03857/) (2018)
- [Domain Enhanced Arbitrary Image Style Transfer via Contrastive Learning](https://mlsanity.com/paper/2205.09542/) (2022)
- [Recognizing Image Style](https://mlsanity.com/paper/1311.3715/) (2013)
- [BAM! The Behance Artistic Media Dataset for Recognition Beyond Photography](https://mlsanity.com/paper/1704.08614/) (2017)
- [ALADIN: All Layer Adaptive Instance Normalization for Fine-grained Style Similarity](https://mlsanity.com/paper/2103.09776/) (2021)
- [In the light of feature distributions: moment matching for Neural Style Transfer](https://mlsanity.com/paper/2103.07208/) (2021)
- [CoGS: Controllable Generation and Search from Sketch and Style](https://mlsanity.com/paper/2203.09554/) (2022)
- [Consistent Style Transfer](https://mlsanity.com/paper/2201.02233/) (2022)
- [StyleBabel: Artistic Style Tagging and Captioning](https://mlsanity.com/paper/2203.05321/) (2022)
- [HyperNST: Hyper-Networks for Neural Style Transfer](https://mlsanity.com/paper/2208.04807/) (2022)
- [PARASOL: Parametric Style Control for Diffusion Image Synthesis](https://mlsanity.com/paper/2303.06464/) (2023)
- [NeAT: Neural Artistic Tracing for Beautiful Style Transfer](https://mlsanity.com/paper/2304.05139/) (2023)

## Built on by (most cited first, 3 of 3)

- [DIFF-NST: Diffusion Interleaving For deFormable Neural Style Transfer](https://mlsanity.com/paper/2307.04157/) (2023)
- [Diffusion Features to Bridge Domain Gap for Semantic Segmentation](https://mlsanity.com/paper/2406.00777/) (2024)
- [Stylistic-STORM (ST-STORM) : Perceiving the Semantic Nature of Appearance](https://mlsanity.com/paper/2604.16086/) (2026)

## Abstract (arXiv)

Representation learning aims to discover individual salient features of a domain in a compact and descriptive form that strongly identifies the unique characteristics of a given sample respective to its domain. Existing works in visual style representation literature have tried to disentangle style from content during training explicitly. A complete separation between these has yet to be fully achieved. Our paper aims to learn a representation of visual artistic style more strongly disentangled from the semantic content depicted in an image. We use Neural Style Transfer (NST) to measure and drive the learning signal and achieve state-of-the-art representation learning on explicitly disentangled metrics. We show that strongly addressing the disentanglement of style and content leads to large gains in style-specific metrics, encoding far less semantic information and achieving state-of-the-art accuracy in downstream multimodal applications.