# SAT: Self-adaptive training for fashion compatibility prediction

arXiv: https://arxiv.org/abs/2206.12622 · HTML: https://mlsanity.com/paper/2206.12622/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 18 references that are in the map.
- First posted on arXiv 25 Jun 2022.

## Builds on (most cited first, 11 of 11)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [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)
- [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)
- [Self-supervised Visual Attribute Learning for Fashion Compatibility](https://mlsanity.com/paper/2008.00348/) (2020)
- [Outfit Generation and Style Extraction via Bidirectional LSTM and Autoencoder](https://mlsanity.com/paper/1807.03133/) (2018)
- [Learning Diverse Fashion Collocation by Neural Graph Filtering](https://mlsanity.com/paper/2003.04888/) (2020)
- [Semi-Supervised Visual Representation Learning for Fashion Compatibility](https://mlsanity.com/paper/2109.08052/) (2021)
- [Learning fashion compatibility across apparel categories for outfit recommendation](https://mlsanity.com/paper/1905.03703/) (2019)

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

- [Attribute-Guided Multi-Level Attention Network for Fine-Grained Fashion Retrieval](https://mlsanity.com/paper/2301.13014/) (2022)
- [A Multihead Continual Learning Framework for Fine-Grained Fashion Image Retrieval with Contrastive Learning and Exponential Moving Average Distillation](https://mlsanity.com/paper/2603.20648/) (2026)
- [Semi-supervised Fashion Compatibility Prediction by Color Distortion Prediction](https://mlsanity.com/paper/2212.14680/) (2022)

## Abstract (arXiv)

This paper presents a self-adaptive training (SAT) model for fashion compatibility prediction. It focuses on the learning of some hard items, such as those that share similar color, texture, and pattern features but are considered incompatible due to the aesthetics or temporal shifts. Specifically, we first design a method to define hard outfits and a difficulty score (DS) is defined and assigned to each outfit based on the difficulty in recommending an item for it. Then, we propose a self-adaptive triplet loss (SATL), where the DS of the outfit is considered. Finally, we propose a very simple conditional similarity network combining the proposed SATL to achieve the learning of hard items in the fashion compatibility prediction. Experiments on the publicly available Polyvore Outfits and Polyvore Outfits-D datasets demonstrate our SAT's effectiveness in fashion compatibility prediction. Besides, our SATL can be easily extended to other conditional similarity networks to improve their performance.