Image-based Recommendations on Styles and Substitutes

TL;DR

This paper presents a scalable, appearance-based model for understanding and recommending visual relationships between objects, such as clothing items, using large datasets and network inference techniques.

Contribution

It introduces a large-scale dataset and a novel network inference method to model human-like visual relationships without relying on detailed annotations.

Findings

Effective in recommending compatible clothing and accessories

Capable of distinguishing complementary and substitute relationships

Scalable approach suitable for large datasets

Abstract

Humans inevitably develop a sense of the relationships between objects, some of which are based on their appearance. Some pairs of objects might be seen as being alternatives to each other (such as two pairs of jeans), while others may be seen as being complementary (such as a pair of jeans and a matching shirt). This information guides many of the choices that people make, from buying clothes to their interactions with each other. We seek here to model this human sense of the relationships between objects based on their appearance. Our approach is not based on fine-grained modeling of user annotations but rather on capturing the largest dataset possible and developing a scalable method for uncovering human notions of the visual relationships within. We cast this as a network inference problem defined on graphs of related images, and provide a large-scale dataset for the training and evaluation of the same. The system we develop is capable of recommending which clothes and accessories will go well together (and which will not), amongst a host of other applications.