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

TL;DR

This paper introduces ALADIN-NST, a self-supervised method for learning highly disentangled artistic style representations using Neural Style Transfer, improving style-specific metrics and reducing semantic content encoding.

Contribution

It presents a novel self-supervised approach that leverages Neural Style Transfer to achieve superior disentanglement of style from content in visual representations.

Findings

Achieves state-of-the-art style disentanglement metrics.

Encodes less semantic content while maintaining style accuracy.

Enhances downstream multimodal application performance.

Abstract

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.