Neural Compatibility Modeling with Attentive Knowledge Distillation

TL;DR

This paper introduces a neural compatibility model for clothing matching that integrates fashion domain knowledge with deep neural networks using attentive knowledge distillation, improving accuracy over existing methods.

Contribution

It proposes a novel teacher-student neural network framework that incorporates fuzzy fashion rules with varying confidence levels for better clothing compatibility modeling.

Findings

Model outperforms several state-of-the-art baselines.

Incorporating domain knowledge improves matching accuracy.

Reveals new fashion insights from experimental results.

Abstract

Recently, the booming fashion sector and its huge potential benefits have attracted tremendous attention from many research communities. In particular, increasing research efforts have been dedicated to the complementary clothing matching as matching clothes to make a suitable outfit has become a daily headache for many people, especially those who do not have the sense of aesthetics. Thanks to the remarkable success of neural networks in various applications such as image classification and speech recognition, the researchers are enabled to adopt the data-driven learning methods to analyze fashion items. Nevertheless, existing studies overlook the rich valuable knowledge (rules) accumulated in fashion domain, especially the rules regarding clothing matching. Towards this end, in this work, we shed light on complementary clothing matching by integrating the advanced deep neural networks and the rich fashion domain knowledge. Considering that the rules can be fuzzy and different rules may have different confidence levels to different samples, we present a neural compatibility modeling scheme with attentive knowledge distillation based on the teacher-student network scheme. Extensive experiments on the real-world dataset show the superiority of our model over several state-of-the-art baselines. Based upon the comparisons, we observe certain fashion insights that add value to the fashion matching study. As a byproduct, we released the codes, and involved parameters to benefit other researchers.