A Semi-Supervised Attention Model for Identifying Authentic Sneakers
To protect consumers and those who manufacture and sell the products they enjoy, it is important to develop convenient tools to help consumers distinguish an authentic product from a counterfeit one. The advancement of deep learning techniques for fine-grained object recognition creates new possibil...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Tsinghua University Press
2020-03-01
|
| Series: | Big Data Mining and Analytics |
| Subjects: | |
| Online Access: | https://www.sciopen.com/article/10.26599/BDMA.2019.9020017 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832573648892854272 |
|---|---|
| author | Yang Yang Nengjun Zhu Yifeng Wu Jian Cao Dechuan Zhan Hui Xiong |
| author_facet | Yang Yang Nengjun Zhu Yifeng Wu Jian Cao Dechuan Zhan Hui Xiong |
| author_sort | Yang Yang |
| collection | DOAJ |
| description | To protect consumers and those who manufacture and sell the products they enjoy, it is important to develop convenient tools to help consumers distinguish an authentic product from a counterfeit one. The advancement of deep learning techniques for fine-grained object recognition creates new possibilities for genuine product identification. In this paper, we develop a Semi-Supervised Attention (SSA) model to work in conjunction with a large-scale multiple-source dataset named YSneaker, which consists of sneakers from various brands and their authentication results, to identify authentic sneakers. Specifically, the SSA model has a self-attention structure for different images of a labeled sneaker and a novel prototypical loss is designed to exploit unlabeled data within the data structure. The model draws on the weighted average of the output feature representations, where the weights are determined by an additional shallow neural network. This allows the SSA model to focus on the most important images of a sneaker for use in identification. A unique feature of the SSA model is its ability to take advantage of unlabeled data, which can help to further minimize the intra-class variation for more discriminative feature embedding. To validate the model, we collect a large number of labeled and unlabeled sneaker images and perform extensive experimental studies. The results show that YSneaker together with the proposed SSA architecture can identify authentic sneakers with a high accuracy rate. |
| format | Article |
| id | doaj-art-cbdcfb44a9c3484eb54dd9e80f37951b |
| institution | Kabale University |
| issn | 2096-0654 |
| language | English |
| publishDate | 2020-03-01 |
| publisher | Tsinghua University Press |
| record_format | Article |
| series | Big Data Mining and Analytics |
| spelling | doaj-art-cbdcfb44a9c3484eb54dd9e80f37951b2025-02-02T03:45:09ZengTsinghua University PressBig Data Mining and Analytics2096-06542020-03-0131294010.26599/BDMA.2019.9020017A Semi-Supervised Attention Model for Identifying Authentic SneakersYang Yang0Nengjun Zhu1Yifeng Wu2Jian Cao3Dechuan Zhan4Hui Xiong5<institution content-type="dept">National Key Laboratory for Novel Software Technology</institution>, <institution>Nanjing University</institution>, <city>Nanjing</city> <postal-code>210023</postal-code>, <country>China</country>.<institution content-type="dept">Computer Science and Engineering</institution>, <institution>Shanghai Jiao Tong University</institution>, <city>Shanghai</city> <postal-code>200240</postal-code>, <country>China</country>.<institution>Alibaba Company</institution>, <city>Hangzhou</city> <postal-code>310000</postal-code>, <country>China</country>.<institution content-type="dept">Computer Science and Engineering</institution>, <institution>Shanghai Jiao Tong University</institution>, <city>Shanghai</city> <postal-code>200240</postal-code>, <country>China</country>.<institution content-type="dept">National Key Laboratory for Novel Software Technology</institution>, <institution>Nanjing University</institution>, <city>Nanjing</city> <postal-code>210023</postal-code>, <country>China</country>.<institution>Rutgers University</institution>, <city>New York</city>, <state>NJ</state> <postal-code>07102</postal-code>, <country>USA</country>.To protect consumers and those who manufacture and sell the products they enjoy, it is important to develop convenient tools to help consumers distinguish an authentic product from a counterfeit one. The advancement of deep learning techniques for fine-grained object recognition creates new possibilities for genuine product identification. In this paper, we develop a Semi-Supervised Attention (SSA) model to work in conjunction with a large-scale multiple-source dataset named YSneaker, which consists of sneakers from various brands and their authentication results, to identify authentic sneakers. Specifically, the SSA model has a self-attention structure for different images of a labeled sneaker and a novel prototypical loss is designed to exploit unlabeled data within the data structure. The model draws on the weighted average of the output feature representations, where the weights are determined by an additional shallow neural network. This allows the SSA model to focus on the most important images of a sneaker for use in identification. A unique feature of the SSA model is its ability to take advantage of unlabeled data, which can help to further minimize the intra-class variation for more discriminative feature embedding. To validate the model, we collect a large number of labeled and unlabeled sneaker images and perform extensive experimental studies. The results show that YSneaker together with the proposed SSA architecture can identify authentic sneakers with a high accuracy rate.https://www.sciopen.com/article/10.26599/BDMA.2019.9020017sneaker identificationfine-grained classificationmulti-instance learningattention mechanism |
| spellingShingle | Yang Yang Nengjun Zhu Yifeng Wu Jian Cao Dechuan Zhan Hui Xiong A Semi-Supervised Attention Model for Identifying Authentic Sneakers Big Data Mining and Analytics sneaker identification fine-grained classification multi-instance learning attention mechanism |
| title | A Semi-Supervised Attention Model for Identifying Authentic Sneakers |
| title_full | A Semi-Supervised Attention Model for Identifying Authentic Sneakers |
| title_fullStr | A Semi-Supervised Attention Model for Identifying Authentic Sneakers |
| title_full_unstemmed | A Semi-Supervised Attention Model for Identifying Authentic Sneakers |
| title_short | A Semi-Supervised Attention Model for Identifying Authentic Sneakers |
| title_sort | semi supervised attention model for identifying authentic sneakers |
| topic | sneaker identification fine-grained classification multi-instance learning attention mechanism |
| url | https://www.sciopen.com/article/10.26599/BDMA.2019.9020017 |
| work_keys_str_mv | AT yangyang asemisupervisedattentionmodelforidentifyingauthenticsneakers AT nengjunzhu asemisupervisedattentionmodelforidentifyingauthenticsneakers AT yifengwu asemisupervisedattentionmodelforidentifyingauthenticsneakers AT jiancao asemisupervisedattentionmodelforidentifyingauthenticsneakers AT dechuanzhan asemisupervisedattentionmodelforidentifyingauthenticsneakers AT huixiong asemisupervisedattentionmodelforidentifyingauthenticsneakers AT yangyang semisupervisedattentionmodelforidentifyingauthenticsneakers AT nengjunzhu semisupervisedattentionmodelforidentifyingauthenticsneakers AT yifengwu semisupervisedattentionmodelforidentifyingauthenticsneakers AT jiancao semisupervisedattentionmodelforidentifyingauthenticsneakers AT dechuanzhan semisupervisedattentionmodelforidentifyingauthenticsneakers AT huixiong semisupervisedattentionmodelforidentifyingauthenticsneakers |