Publication Type
Conference Proceeding Article
Version
publishedVersion
Publication Date
7-2024
Abstract
Outfit Recommendation (OR) in the fashion domain has evolved through two stages: Pre-defined Outfit Recommendation and Personalized Outfit Composition. However, both stages are constrained by existing fashion products, limiting their effectiveness in addressing users' diverse fashion needs. Recently, the advent of AI-generated content provides the opportunity for OR to transcend these limitations, showcasing the potential for personalized outfit generation and recommendation.To this end, we introduce a novel task called Generative Outfit Recommendation (GOR), aiming to generate a set of fashion images and compose them into a visually compatible outfit tailored to specific users. The key objectives of GOR lie in the high fidelity, compatibility, and personalization of generated outfits. To achieve these, we propose a generative outfit recommender model named DiFashion, which empowers exceptional diffusion models to accomplish the parallel generation of multiple fashion images. To ensure three objectives, we design three kinds of conditions to guide the parallel generation process and adopt Classifier-Free-Guidance to enhance the alignment between the generated images and conditions. We apply DiFashion on both personalized Fill-In-The-Blank and GOR tasks and conduct extensive experiments on iFashion and Polyvore-U datasets. The quantitative and human-involved qualitative evaluation demonstrate the superiority of DiFashion over competitive baselines.
Keywords
Generative Outfit Recommendation, Generative RecommenderModel, Diffusion Model
Discipline
Artificial Intelligence and Robotics | Databases and Information Systems
Research Areas
Intelligent Systems and Optimization
Areas of Excellence
Digital transformation
Publication
SIGIR '24: Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, Washington, USA, July 14-18
First Page
1350
Last Page
1359
Identifier
10.1145/3626772.3657719
Publisher
ACM
City or Country
New York
Citation
XU, Yiyan; WANG, Wenjie; FENG, Fuli; MA, Yunshan; ZHANG, Jizhi; and HE, Xiangnan.
Diffusion models for generative outfit recommendation. (2024). SIGIR '24: Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, Washington, USA, July 14-18. 1350-1359.
Available at: https://ink.library.smu.edu.sg/sis_research/10900
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.