skip to main content
10.1145/3366423.3380094acmconferencesArticle/Chapter ViewAbstractPublication PagesthewebconfConference Proceedingsconference-collections
research-article

Metric Learning with Equidistant and Equidistributed Triplet-based Loss for Product Image Search

Published: 20 April 2020 Publication History

Abstract

Product image search in E-commerce systems is a challenging task, because of a huge number of product classes, low intra-class similarity and high inter-class similarity. Deep metric learning, based on paired distances independent of the number of classes, aims to minimize intra-class variances and inter-class similarity in feature embedding space. Most existing approaches strictly restrict the distance between samples with fixed values to distinguish different classes of samples. However, the distance of paired samples has various magnitudes during different training stages. Therefore, it is difficult to directly restrict absolute distances with fixed values. In this paper, we propose a novel Equidistant and Equidistributed Triplet-based (EET) loss function to adjust the distance between samples with relative distance constraints. By optimizing the loss function, the algorithm progressively maximizes intra-class similarity and inter-class variances. Specifically, 1) the equidistant loss pulls the matched samples closer by adaptively constraining two samples of the same class to be equally distant from another one of a different class in each triplet, 2) the equidistributed loss pushes the mismatched samples farther away by guiding different classes to be uniformly distributed while keeping intra-class structure compact in embedding space. Extensive experimental results on product search benchmarks verify the improved performance of our method. We also achieve improvements on other retrieval datasets, which show superior generalization capacity of our method in image search.

References

[1]
Shuo Chen, Chen Gong, Jian Yang, Ying Tai, Le Hui, and Jun Li. 2019. Data-Adaptive Metric Learning with Scale Alignment. In AAAI.
[2]
Weihua Chen, Xiaotang Chen, Jianguo Zhang, and Kaiqi Huang. 2017. Beyond triplet loss: a deep quadruplet network for person re-identification. In CVPR.
[3]
De Cheng, Yihong Gong, Sanping Zhou, Jinjun Wang, and Nanning Zheng. 2016. Person re-identification by multi-channel parts-based cnn with improved triplet loss function. In CVPR.
[4]
Shengyong Ding, Liang Lin, Guangrun Wang, and Hongyang Chao. 2015. Deep feature learning with relative distance comparison for person re-identification. PR (2015).
[5]
Yueqi Duan, Jiwen Lu, and Jie Zhou. 2019. UniformFace: Learning Deep Equidistributed Representation for Face Recognition. In CVPR.
[6]
Weifeng Ge. 2018. Deep metric learning with hierarchical triplet loss. In ECCV.
[7]
Raia Hadsell, Sumit Chopra, and Yann LeCun. 2006. Dimensionality reduction by learning an invariant mapping. In CVPR.
[8]
Ben Harwood, BG Kumar, Gustavo Carneiro, Ian Reid, Tom Drummond, 2017. Smart mining for deep metric learning. In CVPR.
[9]
Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR.
[10]
Alexander Hermans, Lucas Beyer, and Bastian Leibe. 2017. In defense of the triplet loss for person re-identification. In ICCV.
[11]
Elad Hoffer and Nir Ailon. 2015. Deep metric learning using triplet network. In IWSBPR.
[12]
Sergey Ioffe and Christian Szegedy. 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167(2015).
[13]
Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980(2014).
[14]
Jonathan Krause, Michael Stark, Jia Deng, and Li Fei-Fei. 2013. 3d object representations for fine-grained categorization. In ICCVW.
[15]
Marc T Law, Nicolas Thome, and Matthieu Cord. 2013. Quadruplet-wise image similarity learning. In ICCV.
[16]
Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, and Piotr Dollár. 2017. Focal loss for dense object detection. In ICCV.
[17]
Ziwei Liu, Ping Luo, Shi Qiu, Xiaogang Wang, and Xiaoou Tang. 2016. Deepfashion: Powering robust clothes recognition and retrieval with rich annotations. In CVPR.
[18]
Laurens van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. JMLR (2008).
[19]
Yair Movshovitz-Attias, Alexander Toshev, Thomas K Leung, Sergey Ioffe, and Saurabh Singh. 2017. No fuss distance metric learning using proxies. In ICCV.
[20]
Oleg R Musin and Alexey S Tarasov. 2015. The Tammes problem for N= 14. Experimental Mathematics(2015).
[21]
Hyun Oh Song, Stefanie Jegelka, Vivek Rathod, and Kevin Murphy. 2017. Deep metric learning via facility location. In CVPR.
[22]
Hyun Oh Song, Yu Xiang, Stefanie Jegelka, and Silvio Savarese. 2016. Deep metric learning via lifted structured feature embedding. In CVPR.
[23]
Michael Opitz, Georg Waltner, Horst Possegger, and Horst Bischof. 2017. Bier-boosting independent embeddings robustly. In ICCV.
[24]
Michael Opitz, Georg Waltner, Horst Possegger, and Horst Bischof. 2018. Deep metric learning with bier: Boosting independent embeddings robustly. TPAMI (2018).
[25]
Ergys Ristani, Francesco Solera, Roger Zou, Rita Cucchiara, and Carlo Tomasi. 2016. Performance measures and a data set for multi-target, multi-camera tracking. In ECCV.
[26]
Florian Schroff, Dmitry Kalenichenko, and James Philbin. 2015. Facenet: A unified embedding for face recognition and clustering. In CVPR.
[27]
Kihyuk Sohn. 2016. Improved deep metric learning with multi-class n-pair loss objective. In NIPS.
[28]
Catherine Wah, Steve Branson, Peter Welinder, Pietro Perona, and Serge Belongie. 2011. The caltech-ucsd birds-200-2011 dataset. CNS-TR (2011).
[29]
Xun Wang, Xintong Han, Weilin Huang, Dengke Dong, and Matthew R Scott. 2019. Multi-Similarity Loss with General Pair Weighting for Deep Metric Learning. In CVPR.
[30]
Xinshao Wang, Yang Hua, Elyor Kodirov, Guosheng Hu, Romain Garnier, and Neil M. Robertson. 2019. Ranked List Loss for Deep Metric Learning. In CVPR.
[31]
Chao-Yuan Wu, R Manmatha, Alexander J Smola, and Philipp Krahenbuhl. 2017. Sampling matters in deep embedding learning. In ICCV.
[32]
Qiqi Xiao, Hao Luo, and Chi Zhang. 2017. Margin sample mining loss: A deep learning based method for person re-identification. arXiv preprint arXiv:1710.00478(2017).
[33]
Xinyi Xu, Yanhua Yang, Cheng Deng, and Feng Zheng. 2019. Deep Asymmetric Metric Learning via Rich Relationship Mining. In CVPR.
[34]
Jufeng Yang, Dongyu She, Yu-Kun Lai, and Ming-Hsuan Yang. 2018. Retrieving and classifying affective images via deep metric learning. In AAAI.
[35]
Rui Yu, Zhiyong Dou, Song Bai, Zhaoxiang Zhang, Yongchao Xu, and Xiang Bai. 2018. Hard-aware point-to-set deep metric for person re-identification. In ECCV.
[36]
Yuhui Yuan, Kuiyuan Yang, and Chao Zhang. 2017. Hard-aware deeply cascaded embedding. In ICCV.
[37]
Liang Zheng, Liyue Shen, Lu Tian, Shengjin Wang, Jingdong Wang, and Qi Tian. 2015. Scalable person re-identification: A benchmark. In ICCV.
[38]
Wenzhao Zheng, Zhaodong Chen, Jiwen Lu, and Jie Zhou. 2019. Hardness-Aware Deep Metric Learning. In CVPR.
[39]
Sanping Zhou, Jinjun Wang, Jiayun Wang, Yihong Gong, and Nanning Zheng. 2017. Point to set similarity based deep feature learning for person re-identification. In CVPR.
[40]
Bohan Zhuang, Guosheng Lin, Chunhua Shen, and Ian Reid. 2016. Fast training of triplet-based deep binary embedding networks. In CVPR.

Cited By

View all
  • (2023)Spatio-Temporal Variability Analysis of Vegetation Dynamics in China from 2000 to 2022 Based on Leaf Area Index: A Multi-Temporal Image Classification PerspectiveRemote Sensing10.3390/rs1512297515:12(2975)Online publication date: 7-Jun-2023
  • (2023)Rethinking Collaborative Metric Learning: Toward an Efficient Alternative Without Negative SamplingIEEE Transactions on Pattern Analysis and Machine Intelligence10.1109/TPAMI.2022.314109545:1(1017-1035)Online publication date: 1-Jan-2023
  • (2023)Towards Pointsets Representation Learning via Self-Supervised Learning and Set AugmentationIEEE Transactions on Pattern Analysis and Machine Intelligence10.1109/TPAMI.2021.313911345:1(1201-1216)Online publication date: 1-Jan-2023
  • Show More Cited By

Index Terms

  1. Metric Learning with Equidistant and Equidistributed Triplet-based Loss for Product Image Search
      Index terms have been assigned to the content through auto-classification.

      Recommendations

      Comments

      Information & Contributors

      Information

      Published In

      cover image ACM Conferences
      WWW '20: Proceedings of The Web Conference 2020
      April 2020
      3143 pages
      ISBN:9781450370233
      DOI:10.1145/3366423
      Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

      Sponsors

      Publisher

      Association for Computing Machinery

      New York, NY, United States

      Publication History

      Published: 20 April 2020

      Permissions

      Request permissions for this article.

      Check for updates

      Author Tags

      1. Equidistant Loss and Equidistributed Loss
      2. Metric Learning
      3. Product Image Search
      4. Triplet-based Loss

      Qualifiers

      • Research-article
      • Research
      • Refereed limited

      Conference

      WWW '20
      Sponsor:
      WWW '20: The Web Conference 2020
      April 20 - 24, 2020
      Taipei, Taiwan

      Acceptance Rates

      Overall Acceptance Rate 1,899 of 8,196 submissions, 23%

      Contributors

      Other Metrics

      Bibliometrics & Citations

      Bibliometrics

      Article Metrics

      • Downloads (Last 12 months)29
      • Downloads (Last 6 weeks)4
      Reflects downloads up to 17 Feb 2025

      Other Metrics

      Citations

      Cited By

      View all
      • (2023)Spatio-Temporal Variability Analysis of Vegetation Dynamics in China from 2000 to 2022 Based on Leaf Area Index: A Multi-Temporal Image Classification PerspectiveRemote Sensing10.3390/rs1512297515:12(2975)Online publication date: 7-Jun-2023
      • (2023)Rethinking Collaborative Metric Learning: Toward an Efficient Alternative Without Negative SamplingIEEE Transactions on Pattern Analysis and Machine Intelligence10.1109/TPAMI.2022.314109545:1(1017-1035)Online publication date: 1-Jan-2023
      • (2023)Towards Pointsets Representation Learning via Self-Supervised Learning and Set AugmentationIEEE Transactions on Pattern Analysis and Machine Intelligence10.1109/TPAMI.2021.313911345:1(1201-1216)Online publication date: 1-Jan-2023
      • (2023)Boundary-aware Backward-Compatible Representation via Adversarial Learning in Image Retrieval2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)10.1109/CVPR52729.2023.01459(15201-15210)Online publication date: Jun-2023
      • (2022)Fractal Parallel ComputingIntelligent Computing10.34133/2022/97976232022Online publication date: 5-Sep-2022
      • (2022)Towards Interpretable Feature Representation for Domain Adaptation Problem2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI)10.1109/ICTAI56018.2022.00018(61-68)Online publication date: Oct-2022
      • (2021)Learning Segment Similarity and Alignment in Large-Scale Content Based Video RetrievalProceedings of the 29th ACM International Conference on Multimedia10.1145/3474085.3475301(1618-1626)Online publication date: 17-Oct-2021
      • (2021)Fast and Robust Online Traffic Classification Supporting Unseen Applications2021 IEEE Global Communications Conference (GLOBECOM)10.1109/GLOBECOM46510.2021.9685631(1-6)Online publication date: 7-Dec-2021
      • (2021)Discrimination-Aware Mechanism for Fine-grained Representation Learning2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)10.1109/CVPR46437.2021.00087(813-822)Online publication date: Jun-2021

      View Options

      Login options

      View options

      PDF

      View or Download as a PDF file.

      PDF

      eReader

      View online with eReader.

      eReader

      HTML Format

      View this article in HTML Format.

      HTML Format

      Figures

      Tables

      Media

      Share

      Share

      Share this Publication link

      Share on social media