# Learning Fashion Compatibility from In-the-wild Images

arXiv: https://arxiv.org/abs/2206.05982 · HTML: https://mlsanity.com/paper/2206.05982/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 30 references that are in the map.
- First posted on arXiv 13 Jun 2022.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1603.09246/) (2016)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [Colorful Image Colorization](https://mlsanity.com/paper/1603.08511/) (2016)
- [Learning from Simulated and Unsupervised Images through Adversarial Training](https://mlsanity.com/paper/1612.07828/) (2016)
- [Local Aggregation for Unsupervised Learning of Visual Embeddings](https://mlsanity.com/paper/1903.12355/) (2019)
- [Scaling and Benchmarking Self-Supervised Visual Representation Learning](https://mlsanity.com/paper/1905.01235/) (2019)
- [Censoring Representations with an Adversary](https://mlsanity.com/paper/1511.05897/) (2015)
- [Representation Learning by Learning to Count](https://mlsanity.com/paper/1708.06734/) (2017)
- [Learning Fashion Compatibility with Bidirectional LSTMs](https://mlsanity.com/paper/1707.05691/) (2017)
- [Learning Type-Aware Embeddings for Fashion Compatibility](https://mlsanity.com/paper/1803.09196/) (2018)
- [Fashionpedia: Ontology, Segmentation, and an Attribute Localization Dataset](https://mlsanity.com/paper/2004.12276/) (2020)
- [Fashion Outfit Complementary Item Retrieval](https://mlsanity.com/paper/1912.08967/) (2019)
- [Learning Similarity Conditions Without Explicit Supervision](https://mlsanity.com/paper/1908.08589/) (2019)
- [ModaNet: A Large-Scale Street Fashion Dataset with Polygon Annotations](https://mlsanity.com/paper/1807.01394/) (2018)
- [Context-Aware Visual Compatibility Prediction](https://mlsanity.com/paper/1902.03646/) (2019)
- [Creating Capsule Wardrobes from Fashion Images](https://mlsanity.com/paper/1712.02662/) (2017)
- [Self-supervised Visual Attribute Learning for Fashion Compatibility](https://mlsanity.com/paper/2008.00348/) (2020)

## Abstract (arXiv)

Complementary fashion recommendation aims at identifying items from different categories (e.g. shirt, footwear, etc.) that "go well together" as an outfit. Most existing approaches learn representation for this task using labeled outfit datasets containing manually curated compatible item combinations. In this work, we propose to learn representations for compatibility prediction from in-the-wild street fashion images through self-supervised learning by leveraging the fact that people often wear compatible outfits. Our pretext task is formulated such that the representations of different items worn by the same person are closer compared to those worn by other people. Additionally, to reduce the domain gap between in-the-wild and catalog images during inference, we introduce an adversarial loss that minimizes the difference in feature distribution between the two domains. We conduct our experiments on two popular fashion compatibility benchmarks - Polyvore and Polyvore-Disjoint outfits, and outperform existing self-supervised approaches, particularly significant in cross-dataset setting where training and testing images are from different sources.