Cross-domain beauty item retrieval via unsupervised embedding learning

Zehang LIN, Haoran XIE, Peipei KANG, Zhenguo YANG, Wenyin LIU*, Qing LI

*Corresponding author for this work

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)

Abstract

Cross-domain1 image retrieval is always encountering insufficient labelled data in real world. In this paper, we propose unsupervised embedding learning (UEL) for cross-domain beauty and personal care product retrieval to finetune the convolutional neural network (CNN). More specifically, UEL utilizes the non-parametric softmax to train the CNN model as instance-level classification, which reduces the influence of some inevitable problems (e.g., shape variations). In order to obtain better performance, we integrate a few existing retrieval methods trained on different datasets. Furthermore, a query expansion strategy (i.e., diffusion) is adopted to improve the performance. Extensive experiments conducted on a dataset including half million images of beauty and personal product items (Perfect-500K) manifest the effectiveness of our proposed method. Our approach achieves the 2nd place in the leader board of the Grand Challenge of AI Meets Beauty in ACM Multimedia 2019. Our code is available at: https://github.com/RetrainIt/Perfect-Half-Million-Beauty-Product-Image-Recognition-Challenge-2019.

Original languageEnglish
Title of host publicationMM' 2019 : proceedings of the 27th ACM International Conference on Multimedia
Place of Publication9781450367936
PublisherAssociation for Computing Machinery, Inc
Pages2543-2547
Number of pages5
ISBN (Electronic)9781450368896
DOIs
Publication statusPublished - 15 Oct 2019
Externally publishedYes
Event27th ACM International Conference on Multimedia - Nice, France
Duration: 21 Oct 201925 Oct 2019

Conference

Conference27th ACM International Conference on Multimedia
Abbreviated titleMM'19
CountryFrance
CityNice
Period21/10/1925/10/19

    Fingerprint

Bibliographical note

This work is supported by the National Natural Science Foundation of China (No.61703109, No.91748107), and the Guangdong Innovative Research Team Program (No. 2014ZT05G157).

Keywords

  • Cross-domain image retrieval
  • Query expansion
  • UEL

Cite this

LIN, Z., XIE, H., KANG, P., YANG, Z., LIU, W., & LI, Q. (2019). Cross-domain beauty item retrieval via unsupervised embedding learning. In MM' 2019 : proceedings of the 27th ACM International Conference on Multimedia (pp. 2543-2547). Association for Computing Machinery, Inc. https://doi.org/10.1145/3343031.3356055