research-article

A New Similarity Space Tailored for Supervised Deep Metric Learning

Authors:

Fabiane Queiroz,

Flávio Figueiredo,

Jefersson A. Dos Santos,

Heitor RamosAuthors Info & Claims

ACM Transactions on Intelligent Systems and Technology, Volume 14, Issue 1

Article No.: 16, Pages 1 - 25

https://doi.org/10.1145/3559766

Published: 09 November 2022 Publication History

Abstract

We propose a novel deep metric learning method. Differently from many works in this area, we define a novel latent space obtained through an autoencoder. The new space, namely S-space, is divided into different regions describing positions where pairs of objects are similar/dissimilar. We locate makers to identify these regions and estimate the similarities between objects through a kernel-based Cauchy distribution to measure the markers’ distance and the new data representation. In our approach, we simultaneously estimate the markers’ position in the S-space and represent the objects in the same space. Moreover, we propose a new regularization function to prevent similar markers from collapsing altogether. Our method emphasizes the group property (separability) while preserving instance representativity. We present evidence that our proposal can represent complex spaces, for instance, when groups of similar objects are located in disjoint regions. We compare our proposal to nine different distance metric learning approaches (four of them are based on deep learning) on 28 real-world heterogeneous datasets. According to the four quantitative metrics used, our method overcomes all of the nine strategies from the literature.

References

[1]

E. Ahmed, M. Jones, and T. K. Marks. 2015. An improved deep learning architecture for person re-identification. In Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR’15). IEEE, Los Alamitos, CA, 3908–3916.

[2]

Jane Bromley, Isabelle Guyon, Yann LeCun, Eduard Säckinger, and Roopak Shah. 1994. Signature verification using a “Siamese” time delay neural network. In Advances in Neural Information Processing Systems (NeurIPS’94). 737–744.

[3]

F. Cakir, K. He, X. Xia, B. Kulis, and S. Sclaroff. 2019. Deep metric learning to rank. In Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR’19). IEEE, Los Alamitos, CA, 1861–1870.

[4]

Xianghai Cao, Yiming Ge, Renjie Li, Jing Zhao, and Licheng Jiao. 2019. Hyperspectral imagery classification with deep metric learning. Neurocomputing 356 (2019), 217–227.

Digital Library

[5]

Kaixuan Chen, Lina Yao, Dalin Zhang, Xianzhi Wang, Xiaojun Chang, and Feiping Nie. 2020. A semisupervised recurrent convolutional attention model for human activity recognition. IEEE Transactions on Neural Networks and Learning Systems 31, 5 (2020), 1747–1756.

[6]

G. Cheng, C. Yang, X. Yao, L. Guo, and J. Han. 2018. When deep learning meets metric learning: Remote sensing image scene classification via learning discriminative CNNs. IEEE Transactions on Geoscience and Remote Sensing 56, 5 (May 2018), 2811–2821.

[7]

Sumit Chopra, Raia Hadsell, and Yann LeCun. 2005. Learning a similarity metric discriminatively, with application to face verification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’05). IEEE, Los Alamitos, CA, 539–546.

Digital Library

[8]

Yin Cui, Feng Zhou, Yuanqing Lin, and Serge Belongie. 2016. Fine-grained categorization and dataset bootstrapping using deep metric learning with humans in the loop. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’16). IEEE, Los Alamitos, CA, 101–110.

[9]

Jason V. Davis, Brian Kulis, Prateek Jain, Suvrit Sra, and Inderjit S. Dhillon. 2007. Information-theoretic metric learning. In Proceedings of the International Conference on Machine Learning (ICML’07). 209–216.

Digital Library

[10]

Roy De Maesschalck, Delphine Jouan-Rimbaud, and Désiré L. Massart. 2000. The Mahalanobis distance. Chemometrics and Intelligent Laboratory Systems 50, 1 (2000), 1–18.

[11]

Zhenyun Deng, Xiaoshu Zhu, Debo Cheng, Ming Zong, and Shichao Zhang. 2016. Efficient kNN classification algorithm for big data. Neurocomputing 195 (2016), 143–148.

Digital Library

[12]

Michel Deudon. 2018. Learning semantic similarity in a continuous space. In Advances in Neural Information Processing Systems (NeurIPS’18). 986–997.

[13]

K. G. Dizaji, A. Herandi, C. Deng, W. Cai, and H. Huang. 2017. Deep clustering via joint convolutional autoencoder embedding and relative entropy minimization. In Proceedings of the International Conference on Computer Vision (ICCV’17). IEEE, Los Alamitos, CA, 5747–5756.

[14]

Amir Globerson and Sam Roweis. 2005. Metric learning by collapsing classes. In Proceedings of the International Conference on Neural Information Processing Systems (NIPS’05). 451–458.

[15]

Jacob Goldberger, Geoffrey E. Hinton, Sam T. Roweis, and Russ R. Salakhutdinov. 2005. Neighbourhood components analysis. In Advances in Neural Information Processing Systems (NeurIPS’05). 513–520.

[16]

Ian Goodfellow, Yoshua Bengio, and Aaron Courville. 2016. Deep Learning. MIT Press, Cambridge, MA.

Digital Library

[17]

Raia Hadsell, Sumit Chopra, and Yann LeCun. 2006. Dimensionality reduction by learning an invariant mapping. In Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’06), Vol. 2. IEEE, Los Alamitos, CA, 1735–1742.

Digital Library

[18]

Hecht-Nielsen. 1989. Theory of the backpropagation neural network. In Proceedings of the Conference on Neural Networks. 593–605.

[19]

Xiaoyan Hong, Mario Gerla, Guangyu Pei, and Ching-Chuan Chiang. 1999. A group mobility model for ad hoc wireless networks. In Proceedings of the International Workshop on Modeling, Analysis, and Simulation of Wireless and Mobile Systems. 53–60.

Digital Library

[20]

Ruibing Hou, Bingpeng Ma, Hong Chang, Xinqian Gu, Shiguang Shan, and Xilin Chen. 2019. Interaction-and-aggregation network for person re-identification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’19). IEEE, Los Alamitos, CA, 9317–9326.

[21]

Mengdi Huai, Chenglin Miao, Yaliang Li, Qiuling Suo, Lu Su, and Aidong Zhang. 2018. Metric learning from probabilistic labels. In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 1541–1550.

Digital Library

[22]

Sho Inaba, Carl T. Fakhry, Rahul V. Kulkarni, and Kourosh Zarringhalam. 2019. A free energy based approach for distance metric learning. In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 5–13.

Digital Library

[23]

Shichao Kan, Linna Zhang, Zhihai He, Yigang Cen, Shiming Chen, and Jikun Zhou. 2020. Metric learning-based kernel transformer with triplets and label constraints for feature fusion. Pattern Recognition 99 (2020), 107086.

Digital Library

[24]

Gregory Koch, Richard Zemel, and Ruslan Salakhutdinov. 2015. Siamese neural networks for one-shot image recognition. In Proceedings of the ICML Deep Learning Workshop, Vol. 2.

[25]

Fengfu Li, Hong Qiao, and Bo Zhang. 2018. Discriminatively boosted image clustering with fully convolutional auto-encoders. Pattern Recognition 83 (2018), 161–173.

Digital Library

[26]

Yunfan Li, Peng Hu, Zitao Liu, Dezhong Peng, Joey Tianyi Zhou, and Xi Peng. 2021. Contrastive clustering. Proceedings of the AAAI Conference on Artificial Intelligence 35, 10 (May 2021), 8547–8555.

[27]

Y. Lin, J. Jiang, and S. Lee. 2014. A similarity measure for text classification and clustering. IEEE Transactions on Knowledge and Data Engineering 26, 7 (2014), 1575–1590.

[28]

Yiding Liu, Kaiqi Zhao, and Gao Cong. 2018. Efficient similar region search with deep metric learning. In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 1850–1859.

Digital Library

[29]

S. Lloyd. 1982. Least squares quantization in PCM. IEEE Transactions on Information Theory 28, 2 (March 1982), 129–137.

Digital Library

[30]

Minnan Luo, Xiaojun Chang, Liqiang Nie, Yi Yang, Alexander G. Hauptmann, and Qinghua Zheng. 2018. An adaptive semisupervised feature analysis for video semantic recognition. IEEE Transactions on Cybernetics 48, 2 (2018), 648–660.

[31]

Laurens van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of Machine Learning Research 9 (Nov. 2008), 2579–2605.

[32]

Chengzhi Mao, Ziyuan Zhong, Junfeng Yang, Carl Vondrick, and Baishakhi Ray. 2019. Metric learning for adversarial robustness. In Advances in Neural Information Processing Systems (NeurIPS’19). 480–491.

[33]

Brian McFee and Gert R. Lanckriet. 2010. Metric learning to rank. In Proceedings of the International Conference on Machine Learning (ICML’10). 775–782.

[34]

S. Mika, G. Ratsch, J. Weston, B. Scholkopf, and K. R. Mullers. 1999. Fisher discriminant analysis with kernels. In Neural Networks for Signal Processing. IEEE, Los Alamitos, CA, 41–48.

[35]

Vinod Nair and Geoffrey E. Hinton. 2010. Rectified linear units improve restricted Boltzmann machines. In Proceedings of the International Conference on Machine Learning (ICML’10). 807–814.

[36]

B. Nguyen and B. De Baets. 2019. Kernel-based distance metric learning for supervised k-means clustering. IEEE Transactions on Neural Networks and Learning Systems 30, 10 (Oct. 2019), 3084–3095.

[37]

Bac Nguyen and Bernard De Baets. 2020. Improved deep embedding learning based on stochastic symmetric triplet loss and local sampling. Neurocomputing 402 (2020), 209–219.

[38]

Bac Nguyen, Carlos Morell, and Bernard De Baets. 2017. Supervised distance metric learning through maximization of the Jeffrey divergence. Pattern Recognition 64 (2017), 215–225.

Digital Library

[39]

Marc Niethammer, Roland Kwitt, and Francois-Xavier Vialard. 2019. Metric learning for image registration. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’19). IEEE, Los Alamitos, CA, 8463–8472.

[40]

Hyun Oh Song, Yu Xiang, Stefanie Jegelka, and Silvio Savarese. 2016. Deep metric learning via lifted structured feature embedding. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’16). IEEE, Los Alamitos, CA, 4004–4012.

[41]

Thiago M. Paixao, Rodrigo F. Berriel, Maria C. S. Boeres, Alessandro L. Koerich, Claudine Badue, Alberto F. De Souza, and Thiago Oliveira-Santos. 2020. Fast(er) reconstruction of shredded text documents via self-supervised deep asymmetric metric learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR’20). IEEE, Los Alamitos, CA, 14343–14351.

[42]

Xi Peng, Yunfan Li, Ivor W. Tsang, Hongyuan Zhu, Jiancheng Lv, and Joey Tianyi Zhou. 2022. XAI beyond classification: Interpretable neural clustering. Journal of Machine Learning Research 23, 6 (2022), 1–28.

[43]

Xi Peng, Shijie Xiao, Jiashi Feng, Wei-Yun Yau, and Zhang Yi. 2016. Deep subspace clustering with sparsity prior. In Proceedings of the 25th International Joint Conference on Artificial Intelligence (IJCAI’16). 1925–1931.

[44]

Florian Schroff, Dmitry Kalenichenko, and James Philbin. 2015. FaceNet: A unified embedding for face recognition and clustering. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’15). IEEE, Los Alamitos, CA, 815–823.

[45]

Chen Shen, Zhongming Jin, Yiru Zhao, Zhihang Fu, Rongxin Jiang, Yaowu Chen, and Xian-Sheng Hua. 2017. Deep siamese network with multi-level similarity perception for person re-identification. In Proceedings of the ACM International Conference on Multimedia. 1942–1950.

Digital Library

[46]

Jiayi Shen, Haochen Wang, Anran Zhang, Qiang Qiu, Xiantong Zhen, and Xianbin Cao. 2020. Model-agnostic metric for zero-shot learning. In Proceedings of the Conference on Applications of Computer Vision (WACV’20). 786–795.

[47]

Hailin Shi, Yang Yang, Xiangyu Zhu, Shengcai Liao, Zhen Lei, Weishi Zheng, and Stan Z. Li. 2016. Embedding deep metric for person re-identification: A study against large variations. In Computer Vision—ECCV 2016, Bastian Leibe, Jiri Matas, Nicu Sebe, and Max Welling (Eds.). Springer International, Cham, Switzerland, 732–748.

[48]

Kihyuk Sohn. 2016. Improved deep metric learning with multi-class N-pair loss objective. In Advances in Neural Information Processing Systems (NeurIPS’16).1857–1865.

[49]

Juan Luis Suárez, Salvador García, and Francisco Herrera. 2020. pyDML: A Python library for distance metric learning. Journal of Machine Learning Research 21, 96 (2020), 1–7. http://jmlr.org/papers/v21/19-864.html.

[50]

Lorenzo Torresani and Kuang-Chih Lee. 2007. Large margin component analysis. In Advances in Neural Information Processing Systems (NeurIPS’07). 1385–1392.

[51]

Isaac Triguero, Sergio González, Jose M. Moyano, Salvador García, Jesús Alcalá-Fdez, Julián Luengo, Alberto Fernández, Maria José del Jesús, Luciano Sánchez, and Francisco Herrera. 2017. KEEL 3.0: An open source software for multi-stage analysis in data mining. International Journal of Computational Intelligence Systems 10, 1 (2017), 1238–1249.

[52]

Evgeniya Ustinova and Victor Lempitsky. 2016. Learning deep embeddings with histogram loss. In Advances in Neural Information Processing Systems 29, D. D. Lee, M. Sugiyama, U. V. Luxburg, I. Guyon, and R. Garnett (Eds.). Curran Associates, Red Hook, NY, 4170–4178.

[53]

Robin Vogel, Aurélien Bellet, and Stéphan Clémençon. 2018. A probabilistic theory of supervised similarity learning for pointwise ROC curve optimization. In Proceedings of the International Conference on Machine Learning (ICML’18). 5065–5074.

[54]

Duo Wang, Yu Cheng, Mo Yu, Xiaoxiao Guo, and Tao Zhang. 2019. A hybrid approach with optimization-based and metric-based meta-learner for few-shot learning. Neurocomputing 349 (2019), 202–211.

Digital Library

[55]

F. Wang and C. Zhang. 2007. Feature extraction by maximizing the average neighborhood margin. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’07). IEEE, Los Alamitos, CA, 1–8.

[56]

Jingyan Wang, Xin Gao, Quanquan Wang, and Yongping Li. 2012. ProDis-ContSHC: Learning protein dissimilarity measures and hierarchical context coherently for protein-protein comparison in protein database retrieval. BMC Bioinformatics 13, 7 (May 2012), S2.

[57]

Jian Wang, Feng Zhou, Shilei Wen, Xiao Liu, and Yuanqing Lin. 2017. Deep metric learning with angular loss. In Proceedings of the International Conference on Computer Vision (ICCV’17). IEEE, Los Alamitos, CA, 2593–2601.

[58]

L. Wang, B. Yang, Y. Chen, X. Zhang, and J. Orchard. 2017. Improving neural-network classifiers using nearest neighbor partitioning. IEEE Transactions on Neural Networks and Learning Systems 28, 10 (Oct. 2017), 2255–2267.

[59]

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 Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’19). IEEE, Los Alamitos, CA, 5022–5030.

[60]

Kilian Q. Weinberger and Lawrence K. Saul. 2009. Distance metric learning for large margin nearest neighbor classification. Journal of Machine Learning Research 10 (June 2009), 207–244.

Digital Library

[61]

Chao-Yuan Wu, R. Manmatha, Alexander J. Smola, and Philipp Krahenbuhl. 2017. Sampling matters in deep embedding learning. In Proceedings of the International Conference on Computer Vision. IEEE, Los Alamitos, CA, 2840–2848.

[62]

Hao Wu, Qimin Zhou, Rencan Nie, and Jinde Cao. 2020. Effective metric learning with co-occurrence embedding for collaborative recommendations. Neural Networks 124 (2020), 308–318.

Digital Library

[63]

L. Wu, S. C. H. Hoi, R. Jin, J. Zhu, and N. Yu. 2012. Learning Bregman distance functions for semi-supervised clustering. IEEE Transactions on Knowledge and Data Engineering 24, 3 (2012), 478–491.

Digital Library

[64]

Shiming Xiang, Feiping Nie, and Changshui Zhang. 2008. Learning a Mahalanobis distance metric for data clustering and classification. Pattern Recognition 41, 12 (2008), 3600–3612.

Digital Library

[65]

Junyuan Xie, Ross Girshick, and Ali Farhadi. 2016. Unsupervised deep embedding for clustering analysis. In Proceedings of the International Conference on Machine Learning (ICML’16). 478–487.

[66]

Eric P. Xing, Michael I. Jordan, Stuart J. Russell, and Andrew Y. Ng. 2003. Distance metric learning with application to clustering with side-information. In Advances in Neural Information Processing Systems 15, S. Becker, S. Thrun, and K. Obermayer (Eds.). Curran Associates, Red Hook, NY, 521–528.

Digital Library

[67]

Eric P. Xing, Andrew Y. Ng, Michael I. Jordan, and Stuart Russell. 2002. Distance metric learning, with application to clustering with side-information. In Proceedings of the International Conference on Neural Information Processing Systems (NIPS’02). 521–528.

[68]

Yao Yang, Haoran Chen, and Junming Shao. 2019. Triplet enhanced AutoEncoder: Model-free discriminative network embedding. In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI’19). IEEE, Los Alamitos, CA, 5363–5369.

[69]

Dalin Zhang, Lina Yao, Kaixuan Chen, Sen Wang, Xiaojun Chang, and Yunhao Liu. 2020. Making sense of spatio-temporal preserving representations for EEG-based human intention recognition. IEEE Transactions on Cybernetics 50, 7 (2020), 3033–3044.

[70]

Feng Zheng, Cheng Deng, Xing Sun, Xinyang Jiang, Xiaowei Guo, Zongqiao Yu, Feiyue Huang, and Rongrong Ji. 2019. Pyramidal person re-IDentification via multi-loss dynamic training. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’19). IEEE, Los Alamitos, CA, 8514–8522.

Cited By

Barros PGuevara JVillas LGuidoni DFonseca NRamos H(2024)A Novel Federated Meta-Learning Approach for Discriminating Sedentary Behavior From Wearable DataIEEE Internet of Things Journal10.1109/JIOT.2024.342089111:19(31909-31916)Online publication date: 1-Oct-2024
https://doi.org/10.1109/JIOT.2024.3420891
Barros PGuevara JVillas LGuidoni Dda Fonseca NRamos H(2024)Hierarchical federated learning based on ordinal patterns for detecting sedentary behavior2024 International Joint Conference on Neural Networks (IJCNN)10.1109/IJCNN60899.2024.10650180(1-8)Online publication date: 30-Jun-2024
https://doi.org/10.1109/IJCNN60899.2024.10650180

Index Terms

A New Similarity Space Tailored for Supervised Deep Metric Learning
1. Computing methodologies
  1. Machine learning
    1. Machine learning approaches
      1. Learning latent representations
      2. Neural networks

Recommendations

Fine-grained Patient Similarity Measuring using Deep Metric Learning
CIKM '17: Proceedings of the 2017 ACM on Conference on Information and Knowledge Management

Patient similarity measuring plays a significant role in many healthcare applications, such as cohort study and treatment comparative effectiveness research. Existing methods mainly rely on supervised metric learning method to study patient similarity ...
Attention-Based Ensemble for Deep Metric Learning
Computer Vision – ECCV 2018
Abstract
Deep metric learning aims to learn an embedding function, modeled as deep neural network. This embedding function usually puts semantically similar images close while dissimilar images far from each other in the learned embedding space. Recently, ...
Diversified Mutual Learning for Deep Metric Learning
Computer Vision – ECCV 2020 Workshops
Abstract
Mutual learning is an ensemble training strategy to improve generalization by transferring individual knowledge to each other while simultaneously training multiple models. In this work, we propose an effective mutual learning method for deep ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Transactions on Intelligent Systems and Technology

ACM Transactions on Intelligent Systems and Technology Volume 14, Issue 1

February 2023

487 pages

ISSN:2157-6904

EISSN:2157-6912

DOI:10.1145/3570136

Editor:
Huan Liu
Arizona State University, USA

Issue’s Table of Contents

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].

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 09 November 2022

Online AM: 02 September 2022

Accepted: 24 August 2022

Revised: 22 July 2022

Received: 07 May 2022

Published in TIST Volume 14, Issue 1

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Refereed

Funding Sources

São Paulo Research Foundation (FAPESP)
Coordenação de Aperfeiçoamento de Pessoal de Nível Superior, Brazil (CAPES)
Conselho Nacional de Desenvolvimento Científico e Tecnológico, Brazil (CNPq)
Fundação de Amparo à Pesquisa do Estado de Minas Gerais (FAPEMIG)

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

1
Total Citations
View Citations
320
Total Downloads

Downloads (Last 12 months)108
Downloads (Last 6 weeks)10

Reflects downloads up to 19 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

Barros PGuevara JVillas LGuidoni DFonseca NRamos H(2024)A Novel Federated Meta-Learning Approach for Discriminating Sedentary Behavior From Wearable DataIEEE Internet of Things Journal10.1109/JIOT.2024.342089111:19(31909-31916)Online publication date: 1-Oct-2024
https://doi.org/10.1109/JIOT.2024.3420891
Barros PGuevara JVillas LGuidoni Dda Fonseca NRamos H(2024)Hierarchical federated learning based on ordinal patterns for detecting sedentary behavior2024 International Joint Conference on Neural Networks (IJCNN)10.1109/IJCNN60899.2024.10650180(1-8)Online publication date: 30-Jun-2024
https://doi.org/10.1109/IJCNN60899.2024.10650180

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Article

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Full Text

View this article in Full Text.

HTML Format

View this article in HTML Format.

Media

Figures

Other

Tables

View full text|Download PDF

View Issue’s Table of Contents