SAT: Self-adaptive training for fashion compatibility prediction
This work addresses fashion compatibility prediction for recommendation systems, but it is incremental as it builds on existing conditional similarity networks with a novel loss function.
The paper tackles the problem of fashion compatibility prediction by focusing on hard items with similar features but incompatibility due to aesthetics or temporal shifts, proposing a self-adaptive training model that improves performance on Polyvore datasets.
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.