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.
|Title of host publication||MM' 2019 : proceedings of the 27th ACM International Conference on Multimedia|
|Place of Publication||9781450367936|
|Publisher||Association for Computing Machinery, Inc|
|Number of pages||5|
|Publication status||Published - 15 Oct 2019|
|Event||27th ACM International Conference on Multimedia - Nice, France|
Duration: 21 Oct 2019 → 25 Oct 2019
|Conference||27th ACM International Conference on Multimedia|
|Period||21/10/19 → 25/10/19|
Bibliographical noteThis work is supported by the National Natural Science Foundation of China (No.61703109, No.91748107), and the Guangdong Innovative Research Team Program (No. 2014ZT05G157).
- Cross-domain image retrieval
- Query expansion