# Self-supervised Visual Attribute Learning for Fashion Compatibility

arXiv: https://arxiv.org/abs/2008.00348 · HTML: https://mlsanity.com/paper/2008.00348/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Aug 2020.

## Built on by (most cited first, 12 of 12)

- [GeneCIS: A Benchmark for General Conditional Image Similarity](https://mlsanity.com/paper/2306.07969/) (2023)
- [From Region to Patch: Attribute-Aware Foreground-Background Contrastive Learning for Fine-Grained Fashion Retrieval](https://mlsanity.com/paper/2305.10260/) (2023)
- [Semi-Supervised Visual Representation Learning for Fashion Compatibility](https://mlsanity.com/paper/2109.08052/) (2021)
- [UIGR: Unified Interactive Garment Retrieval](https://mlsanity.com/paper/2204.03111/) (2022)
- [Smart Fashion: A Review of AI Applications in the Fashion & Apparel Industry](https://mlsanity.com/paper/2111.00905/) (2021)
- [SAT: Self-adaptive training for fashion compatibility prediction](https://mlsanity.com/paper/2206.12622/) (2022)
- [Multi-modal Extreme Classification](https://mlsanity.com/paper/2309.04961/) (2023)
- [COutfitGAN: Learning to Synthesize Compatible Outfits Supervised by Silhouette Masks and Fashion Styles](https://mlsanity.com/paper/2502.08674/) (2025)
- [fAshIon after fashion: A Report of AI in Fashion](https://mlsanity.com/paper/2105.03050/) (2021)
- [Learning Fashion Compatibility from In-the-wild Images](https://mlsanity.com/paper/2206.05982/) (2022)
- [Semi-supervised Fashion Compatibility Prediction by Color Distortion Prediction](https://mlsanity.com/paper/2212.14680/) (2022)
- [Towards Intelligent Design: A Self-driven Framework for Collocated Clothing Synthesis Leveraging Fashion Styles and Textures](https://mlsanity.com/paper/2501.13396/) (2025)

## Abstract (arXiv)

Many self-supervised learning (SSL) methods have been successful in learning semantically meaningful visual representations by solving pretext tasks. However, prior work in SSL focuses on tasks like object recognition or detection, which aim to learn object shapes and assume that the features should be invariant to concepts like colors and textures. Thus, these SSL methods perform poorly on downstream tasks where these concepts provide critical information. In this paper, we present an SSL framework that enables us to learn color and texture-aware features without requiring any labels during training. Our approach consists of three self-supervised tasks designed to capture different concepts that are neglected in prior work that we can select from depending on the needs of our downstream tasks. Our tasks include learning to predict color histograms and discriminate shapeless local patches and textures from each instance. We evaluate our approach on fashion compatibility using Polyvore Outfits and In-Shop Clothing Retrieval using Deepfashion, improving upon prior SSL methods by 9.5-16%, and even outperforming some supervised approaches on Polyvore Outfits despite using no labels. We also show that our approach can be used for transfer learning, demonstrating that we can train on one dataset while achieving high performance on a different dataset.