MDiFF: Exploiting Multimodal Score-based Diffusion Models for New Fashion Product Performance Forecasting

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Avogaro, Andrea, Capogrosso, Luigi, Fummi, Franco, Cristani, Marco
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910735829827584
author Avogaro, Andrea
Capogrosso, Luigi
Fummi, Franco
Cristani, Marco
author_facet Avogaro, Andrea
Capogrosso, Luigi
Fummi, Franco
Cristani, Marco
contents The fast fashion industry suffers from significant environmental impacts due to overproduction and unsold inventory. Accurately predicting sales volumes for unreleased products could significantly improve efficiency and resource utilization. However, predicting performance for entirely new items is challenging due to the lack of historical data and rapidly changing trends, and existing deterministic models often struggle with domain shifts when encountering items outside the training data distribution. The recently proposed diffusion models address this issue using a continuous-time diffusion process. This allows us to simulate how new items are adopted, reducing the impact of domain shift challenges faced by deterministic models. As a result, in this paper, we propose MDiFF: a novel two-step multimodal diffusion models-based pipeline for New Fashion Product Performance Forecasting (NFPPF). First, we use a score-based diffusion model to predict multiple future sales for different clothes over time. Then, we refine these multiple predictions with a lightweight Multi-layer Perceptron (MLP) to get the final forecast. MDiFF leverages the strengths of both architectures, resulting in the most accurate and efficient forecasting system for the fast-fashion industry at the state-of-the-art. The code can be found at https://github.com/intelligolabs/MDiFF.
format Preprint
id arxiv_https___arxiv_org_abs_2412_06840
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MDiFF: Exploiting Multimodal Score-based Diffusion Models for New Fashion Product Performance Forecasting
Avogaro, Andrea
Capogrosso, Luigi
Fummi, Franco
Cristani, Marco
Machine Learning
Computer Vision and Pattern Recognition
The fast fashion industry suffers from significant environmental impacts due to overproduction and unsold inventory. Accurately predicting sales volumes for unreleased products could significantly improve efficiency and resource utilization. However, predicting performance for entirely new items is challenging due to the lack of historical data and rapidly changing trends, and existing deterministic models often struggle with domain shifts when encountering items outside the training data distribution. The recently proposed diffusion models address this issue using a continuous-time diffusion process. This allows us to simulate how new items are adopted, reducing the impact of domain shift challenges faced by deterministic models. As a result, in this paper, we propose MDiFF: a novel two-step multimodal diffusion models-based pipeline for New Fashion Product Performance Forecasting (NFPPF). First, we use a score-based diffusion model to predict multiple future sales for different clothes over time. Then, we refine these multiple predictions with a lightweight Multi-layer Perceptron (MLP) to get the final forecast. MDiFF leverages the strengths of both architectures, resulting in the most accurate and efficient forecasting system for the fast-fashion industry at the state-of-the-art. The code can be found at https://github.com/intelligolabs/MDiFF.
title MDiFF: Exploiting Multimodal Score-based Diffusion Models for New Fashion Product Performance Forecasting
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.06840