Article

Order Learning Using Partially Ordered Data via Chainization

Authors:

Chang-Su KimAuthors Info & Claims

Computer Vision – ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part XIII

Pages 196 - 211

https://doi.org/10.1007/978-3-031-19778-9_12

Published: 23 October 2022 Publication History

Abstract

We propose the chainization algorithm for effective order learning when only partially ordered data are available. First, we develop a binary comparator to predict missing ordering relations between instances. Then, by extending the Kahn’s algorithm, we form a chain representing a linear ordering of instances. We fine-tune the comparator over pseudo pairs, which are sampled from the chain, and then re-estimate the linear ordering alternately. As a result, we obtain a more reliable comparator and a more meaningful linear ordering. Experimental results show that the proposed algorithm yields excellent rank estimation performances under various weak supervision scenarios, including semi-supervised learning, domain adaptation, and bipartite cases. The source codes are available at https://github.com/seon92/Chainization.

References

[1]

Barsoum, E., Zhang, C., Ferrer, C.C., Zhang, Z.: Training deep networks for facial expression recognition with crowd-sourced label distribution. In: ICMI (2016)

[2]

Bromley, J., Guyon, I., LeCun, Y., Säckinger, E., Shah, R.: Signature verification using a "Siamese" time delay neural network. In: NIPS (1993)

[3]

Cormen, T.H., Leiserson, C.E., Rivest, R.L., Stein, C.: Introduction to Algorithms. MIT press (2009)

[4]

Diaconis P and Graham RL Spearman’s footrule as a measure of disarray J. Roy. Stat. Soc.: Ser. B (Methodol.) 1977 39 2 262-268

[5]

Diaz, R., Marathe, A.: Soft labels for ordinal regression. In: CVPR (2019)

[6]

Jech, T.J.: The Axiom of Choice. Courier Corporation (2008)

[7]

Kahn AB Topological sorting of large networks Commun. ACM 1962 5 11 558-562

[8]

Knuth DE and Szwarcfiter JL A structured program to generate all topological sorting arrangements Inf. Process. Lett. 1974 2 6 153-157

[9]

Lee, S.H., Kim, C.S.: Deep repulsive clustering of ordered data based on order-identitiy decomposition. In: ICLR (2021)

[10]

Levi, G., Hassner, T.: Age and gender classification using convolutional neural networks. In: CVPR Workshops (2015)

[11]

Li, W., Huang, X., Lu, J., Feng, J., Zhou, J.: Learning probabilistic ordinal embeddings for uncertainty-aware regression. In: CVPR (2021)

[12]

Lim, K., Shin, N.H., Lee, Y.Y., Kim, C.S.: Order learning and its application to age estimation. In: ICLR (2020)

[13]

Liu, X., Li, S., Ge, Y., Ye, P., You, J., Lu, J.: Recursively conditional gaussian for ordinal unsupervised domain adaptation. In: ICCV (2021)

[14]

Liu, Y., Kong, A.W.K., Goh, C.K.: A constrained deep neural network for ordinal regression. In: CVPR (2018)

[15]

Liu, Y., Wang, F., Kong, A.W.K.: Probabilistic deep ordinal regression based on Gaussian processes. In: CVPR (2019)

[16]

Niu, Z., Zhou, M., Wang, L., Gao, X., Hua, G.: Ordinal regression with multiple output CNN for age estimation. In: CVPR (2016)

[17]

Pan, H., Han, H., Shan, S., Chen, X.: Mean-variance loss for deep age estimation from a face. In: CVPR (2018)

[18]

Parikh, D., Grauman, K.: Relative attributes. In: ICCV (2011)

[19]

Pearce DJ and Kelly PH A dynamic topological sort algorithm for directed acyclic graphs J. Exp. Algorithmics 2007 11 1-7

[20]

Reingold, E.M., Nievergelt, J., Deo, N.: Combinatorial Algorithms: Theory and Practice. Prentice Hall (1977)

[21]

Ricanek, K., Tesafaye, T.: MORPH: A longitudinal image database of normal adult age-progression. In: FGR (2006)

[22]

Schifanella, R., Redi, M., Aiello, L.M.: An image is worth more than a thousand favorites: Surfacing the hidden beauty of Flickr pictures. In: ICWSM (2015)

[23]

Schröder, B.S.W.: Ordered Sets: An Introduction. Springer (2003)

[24]

Shin, N.H., Lee, S.H., Kim, C.S.: Moving window regression: a novel approach to ordinal regression. In: CVPR (2022)

[25]

Sohn, K., et al.: FixMatch: simplifying semi-supervised learning with consistency and confidence. In: NIPS (2020)

[26]

Souri, Y., Noury, E., Adeli, E.: Deep relative attributes. In: ACCV (2016)

[27]

Tarjan R Finding dominators in directed graphs SIAM J. Comput. 1974 3 1 62-89

[28]

Zhang, B., et al.: FlexMatch: boosting semi-supervised learning with curriculum pseudo labeling. In: NIPS (2021)

[29]

Zhang, Y., Liu, L., Li, C., Loy, C.C.: Quantifying facial age by posterior of age comparisons. In: BMVC (2017)

[30]

Zou Y, Yang X, Yu Z, Kumar BVKV, and Kautz J Vedaldi A, Bischof H, Brox T, and Frahm J-M Joint disentangling and adaptation for cross-domain person re-identification Computer Vision – ECCV 2020 2020 Cham Springer 87-104

Cited By

Du YZhai QDai WLi X(2024)Teach CLIP to Develop a Number Sense for Ordinal RegressionComputer Vision – ECCV 202410.1007/978-3-031-73013-9_1(1-17)Online publication date: 29-Sep-2024
https://dl.acm.org/doi/10.1007/978-3-031-73013-9_1
Li SGominski DBrandt MTong XCiais P(2024)Get Your Embedding Space in Order: Domain-Adaptive Regression for Forest MonitoringComputer Vision – ECCV 202410.1007/978-3-031-72980-5_6(94-111)Online publication date: 29-Sep-2024
https://dl.acm.org/doi/10.1007/978-3-031-72980-5_6
Kim JYang SJeong SKim C(2024)Forbes: Face Obfuscation Rendering via Backpropagation Refinement SchemeComputer Vision – ECCV 202410.1007/978-3-031-72890-7_4(54-70)Online publication date: 29-Sep-2024
https://dl.acm.org/doi/10.1007/978-3-031-72890-7_4

Index Terms

Order Learning Using Partially Ordered Data via Chainization

Index terms have been assigned to the content through auto-classification.

Recommendations

Practical age estimation using deep label distribution learning
Abstract
Age estimation plays an important role in humancomputer interaction system. The lack of large number of facial images with definite age label makes age estimation algorithms inefficient. Deep label distribution learning (DLDL) which employs ...
Facial expression recognition via learning deep sparse autoencoders

Facial expression recognition is an important research issue in the pattern recognition field. In this paper, we intend to present a novel framework for facial expression recognition to automatically distinguish the expressions with high accuracy. ...
Facial age estimation using pre-trained CNN and transfer learning
Abstract
This paper tackled the problem of human facial age estimation using transfer learning of some pre-trained CNNs, namely VGG, Res-Net, Google-Net, and Alex-Net. Those networks have been fine-tuned with transfer learning and undergone many ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Guide Proceedings

Computer Vision – ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part XIII

Oct 2022

803 pages

ISBN:978-3-031-19777-2

DOI:10.1007/978-3-031-19778-9

Editors:
Shai Avidan
Tel Aviv University, Tel Aviv, Israel
,
Gabriel Brostow
University College London, London, UK
,
Moustapha Cissé
Google AI, Accra, Ghana
,
Giovanni Maria Farinella
University of Catania, Catania, Italy
,
Tal Hassner
Facebook (United States), Menlo Park, CA, USA

© The Author(s), under exclusive license to Springer Nature Switzerland AG 2022.

Publisher

Springer-Verlag

Berlin, Heidelberg

Publication History

Published: 23 October 2022

Author Tags

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

1
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 01 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

Du YZhai QDai WLi X(2024)Teach CLIP to Develop a Number Sense for Ordinal RegressionComputer Vision – ECCV 202410.1007/978-3-031-73013-9_1(1-17)Online publication date: 29-Sep-2024
https://dl.acm.org/doi/10.1007/978-3-031-73013-9_1
Li SGominski DBrandt MTong XCiais P(2024)Get Your Embedding Space in Order: Domain-Adaptive Regression for Forest MonitoringComputer Vision – ECCV 202410.1007/978-3-031-72980-5_6(94-111)Online publication date: 29-Sep-2024
https://dl.acm.org/doi/10.1007/978-3-031-72980-5_6
Kim JYang SJeong SKim C(2024)Forbes: Face Obfuscation Rendering via Backpropagation Refinement SchemeComputer Vision – ECCV 202410.1007/978-3-031-72890-7_4(54-70)Online publication date: 29-Sep-2024
https://dl.acm.org/doi/10.1007/978-3-031-72890-7_4

View Options

View options

Media

Figures

Other

Tables

View Table of Contents