Cargando…

Deep Learning with Discriminative Margin Loss for Cross-Domain Consumer-to-Shop Clothes Retrieval

Consumer-to-shop clothes retrieval refers to the problem of matching photos taken by customers with their counterparts in the shop. Due to some problems, such as a large number of clothing categories, different appearances of clothing items due to different camera angles and shooting conditions, dif...

Descripción completa

Detalles Bibliográficos
Autores principales: Alirezazadeh, Pendar, Dornaika, Fadi, Moujahid, Abdelmalik
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9002530/
https://www.ncbi.nlm.nih.gov/pubmed/35408276
http://dx.doi.org/10.3390/s22072660
_version_ 1784685912707301376
author Alirezazadeh, Pendar
Dornaika, Fadi
Moujahid, Abdelmalik
author_facet Alirezazadeh, Pendar
Dornaika, Fadi
Moujahid, Abdelmalik
author_sort Alirezazadeh, Pendar
collection PubMed
description Consumer-to-shop clothes retrieval refers to the problem of matching photos taken by customers with their counterparts in the shop. Due to some problems, such as a large number of clothing categories, different appearances of clothing items due to different camera angles and shooting conditions, different background environments, and different body postures, the retrieval accuracy of traditional consumer-to-shop models is always low. With advances in convolutional neural networks (CNNs), the accuracy of garment retrieval has been significantly improved. Most approaches addressing this problem use single CNNs in conjunction with a softmax loss function to extract discriminative features. In the fashion domain, negative pairs can have small or large visual differences that make it difficult to minimize intraclass variance and maximize interclass variance with softmax. Margin-based softmax losses such as Additive Margin-Softmax (aka CosFace) improve the discriminative power of the original softmax loss, but since they consider the same margin for the positive and negative pairs, they are not suitable for cross-domain fashion search. In this work, we introduce the cross-domain discriminative margin loss (DML) to deal with the large variability of negative pairs in fashion. DML learns two different margins for positive and negative pairs such that the negative margin is larger than the positive margin, which provides stronger intraclass reduction for negative pairs. The experiments conducted on publicly available fashion datasets DARN and two benchmarks of the DeepFashion dataset—(1) Consumer-to-Shop Clothes Retrieval and (2) InShop Clothes Retrieval—confirm that the proposed loss function not only outperforms the existing loss functions but also achieves the best performance.
format Online
Article
Text
id pubmed-9002530
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-90025302022-04-13 Deep Learning with Discriminative Margin Loss for Cross-Domain Consumer-to-Shop Clothes Retrieval Alirezazadeh, Pendar Dornaika, Fadi Moujahid, Abdelmalik Sensors (Basel) Article Consumer-to-shop clothes retrieval refers to the problem of matching photos taken by customers with their counterparts in the shop. Due to some problems, such as a large number of clothing categories, different appearances of clothing items due to different camera angles and shooting conditions, different background environments, and different body postures, the retrieval accuracy of traditional consumer-to-shop models is always low. With advances in convolutional neural networks (CNNs), the accuracy of garment retrieval has been significantly improved. Most approaches addressing this problem use single CNNs in conjunction with a softmax loss function to extract discriminative features. In the fashion domain, negative pairs can have small or large visual differences that make it difficult to minimize intraclass variance and maximize interclass variance with softmax. Margin-based softmax losses such as Additive Margin-Softmax (aka CosFace) improve the discriminative power of the original softmax loss, but since they consider the same margin for the positive and negative pairs, they are not suitable for cross-domain fashion search. In this work, we introduce the cross-domain discriminative margin loss (DML) to deal with the large variability of negative pairs in fashion. DML learns two different margins for positive and negative pairs such that the negative margin is larger than the positive margin, which provides stronger intraclass reduction for negative pairs. The experiments conducted on publicly available fashion datasets DARN and two benchmarks of the DeepFashion dataset—(1) Consumer-to-Shop Clothes Retrieval and (2) InShop Clothes Retrieval—confirm that the proposed loss function not only outperforms the existing loss functions but also achieves the best performance. MDPI 2022-03-30 /pmc/articles/PMC9002530/ /pubmed/35408276 http://dx.doi.org/10.3390/s22072660 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Alirezazadeh, Pendar
Dornaika, Fadi
Moujahid, Abdelmalik
Deep Learning with Discriminative Margin Loss for Cross-Domain Consumer-to-Shop Clothes Retrieval
title Deep Learning with Discriminative Margin Loss for Cross-Domain Consumer-to-Shop Clothes Retrieval
title_full Deep Learning with Discriminative Margin Loss for Cross-Domain Consumer-to-Shop Clothes Retrieval
title_fullStr Deep Learning with Discriminative Margin Loss for Cross-Domain Consumer-to-Shop Clothes Retrieval
title_full_unstemmed Deep Learning with Discriminative Margin Loss for Cross-Domain Consumer-to-Shop Clothes Retrieval
title_short Deep Learning with Discriminative Margin Loss for Cross-Domain Consumer-to-Shop Clothes Retrieval
title_sort deep learning with discriminative margin loss for cross-domain consumer-to-shop clothes retrieval
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9002530/
https://www.ncbi.nlm.nih.gov/pubmed/35408276
http://dx.doi.org/10.3390/s22072660
work_keys_str_mv AT alirezazadehpendar deeplearningwithdiscriminativemarginlossforcrossdomainconsumertoshopclothesretrieval
AT dornaikafadi deeplearningwithdiscriminativemarginlossforcrossdomainconsumertoshopclothesretrieval
AT moujahidabdelmalik deeplearningwithdiscriminativemarginlossforcrossdomainconsumertoshopclothesretrieval