skip to main content
10.1145/2671188.2749309acmconferencesArticle/Chapter ViewAbstractPublication PagesicmrConference Proceedingsconference-collections
short-paper

Zero-shot Image Categorization by Image Correlation Exploration

Published: 22 June 2015 Publication History

Abstract

The problem of image categorization from zero or only a few training examples, called zero-shot learning, occurs frequently, but it has hardly been studied in computer vision research. To tackle this problem, mid-level semantic attributes are introduced to identify image categories. For example, one can construct a classifier for the giant panda category by enumerating its attributes (e.g., black, white and four-footed) even without providing giant panda training images. Recently, several studies have investigated to learn attribute classifiers, based on which new classes can be detected. However, an often-encountered problem is the limited number of training data due to the time-consuming manual annotation of the attributes. Also, using single feature is hard to detect some attributes, e.g., the HSV feature is not robust enough to predict 'tusk' or 'flies' attributes. In this paper, we propose a unified semi-supervised learning (SSL) framework that learns the attribute classifiers by utilizing multiple feature and exploring the correlations between images. Specifically, we learn an optimal graph which embeds the relationships among the data points more accurately. Then, this graph is used to generate a geometrical regularizers for a semi-supervised learning model to learn the attribute classifier by utilizing both labeled and unlabeled images. Afterward, new classes can be detected based on their attribute representation. The use of SSL can boost the performances of attribute classifiers with very few training examples, and the adoption of multiple features makes the attribute prediction more robust. Experimental results on a series of real benchmark data sets suggest that semi-supervised learning do enhance the performances of attribute prediction and zero-shot categorization, compared with state-of-the-art methods.

References

[1]
M. Chen, A. Zheng, and K. Q. Weinberger. Fast image tagging. In ICML, 2013.
[2]
A. Farhadi, I. Endres, D. Hoiem, and D. A. Forsyth. Describing objects by their attributes. In CVPR, 2009.
[3]
L. Gao, J. Song, F. Nie, Y. Yan, N. Sebe, and H. T. Shen. Optimal graph leaning with partial tags and multiple features for image and video annotation. In CVPR, 2015.
[4]
D. Jayaraman and K. Grauman. Zero-shot recognition with unreliable attributes. In NIPS, 2014.
[5]
D. Jayaraman, F. Sha, and K. Grauman. Decorrelating semantic visual attributes by resisting the urge to share. In CVPR, 2014.
[6]
P. Kankuekul, A. Kawewong, S. Tangruamsub, and O. Hasegawa. Online incremental attribute-based zero-shot learning. In CVPR, 2012.
[7]
C. H. Lampert, H. Nickisch, and S. Harmeling. Attribute-based classification for zero-shot visual object categorization. IEEE Trans. Pattern Anal. Mach. Intell., 36(3):453--465, 2014.
[8]
M. Palatucci, D. Pomerleau, G. E. Hinton, and T. M. Mitchell. Zero-shot learning with semantic output codes. In NIPS, 2009.
[9]
J. Song, Y. Yang, Z. Huang, H. T. Shen, and R. Hong. Multiple feature hashing for real-time large scale near-duplicate video retrieval. In ACM Multimedia, pages 423--432, 2011.
[10]
J. Song, Y. Yang, X. Li, Z. Huang, and Y. Yang. Robust hashing with local models for approximate similarity search. IEEE T. Cybernetics, 44(7):1225--1236, 2014.
[11]
F. X. Yu, L. Cao, R. S. Feris, J. R. Smith, and S. Chang. Designing category-level attributes for discriminative visual recognition. In CVPR, 2013.

Cited By

View all
  • (2022)A study on zero-shot learning from semantic viewpointThe Visual Computer: International Journal of Computer Graphics10.1007/s00371-022-02470-w39:5(2149-2163)Online publication date: 30-May-2022
  • (2021)A novel approach based on fully connected weighted bipartite graph for zero-shot learning problemsJournal of Ambient Intelligence and Humanized Computing10.1007/s12652-020-02615-612:9(8647-8662)Online publication date: 22-Jan-2021
  • (2021)Zero-Shot Learning-Based Detection of Electric Insulators in the WildMachine Learning, Optimization, and Data Science10.1007/978-3-030-95470-3_16(213-225)Online publication date: 4-Oct-2021
  • Show More Cited By

Index Terms

  1. Zero-shot Image Categorization by Image Correlation Exploration

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Conferences
    ICMR '15: Proceedings of the 5th ACM on International Conference on Multimedia Retrieval
    June 2015
    700 pages
    ISBN:9781450332743
    DOI:10.1145/2671188
    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: 22 June 2015

    Permissions

    Request permissions for this article.

    Check for updates

    Author Tags

    1. attributes
    2. image categorization
    3. zero-shot learning

    Qualifiers

    • Short-paper

    Funding Sources

    • Fundamental Research Funds for the Central Universities

    Conference

    ICMR '15
    Sponsor:

    Acceptance Rates

    ICMR '15 Paper Acceptance Rate 48 of 127 submissions, 38%;
    Overall Acceptance Rate 254 of 830 submissions, 31%

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • Downloads (Last 12 months)4
    • Downloads (Last 6 weeks)0
    Reflects downloads up to 17 Feb 2025

    Other Metrics

    Citations

    Cited By

    View all
    • (2022)A study on zero-shot learning from semantic viewpointThe Visual Computer: International Journal of Computer Graphics10.1007/s00371-022-02470-w39:5(2149-2163)Online publication date: 30-May-2022
    • (2021)A novel approach based on fully connected weighted bipartite graph for zero-shot learning problemsJournal of Ambient Intelligence and Humanized Computing10.1007/s12652-020-02615-612:9(8647-8662)Online publication date: 22-Jan-2021
    • (2021)Zero-Shot Learning-Based Detection of Electric Insulators in the WildMachine Learning, Optimization, and Data Science10.1007/978-3-030-95470-3_16(213-225)Online publication date: 4-Oct-2021
    • (2019)A Survey of Zero-Shot LearningACM Transactions on Intelligent Systems and Technology10.1145/329331810:2(1-37)Online publication date: 16-Jan-2019
    • (2019)Inductive Zero-Shot Image Annotation via Embedding GraphIEEE Access10.1109/ACCESS.2019.29253837(107816-107830)Online publication date: 2019
    • (2018)Multiple hierarchical deep hashing for large scale image retrievalMultimedia Tools and Applications10.1007/s11042-017-4489-077:9(10471-10484)Online publication date: 1-May-2018
    • (2017)Low-rank feature selection for multi-view regressionMultimedia Tools and Applications10.1007/s11042-016-4119-276:16(17479-17495)Online publication date: 1-Aug-2017
    • (2017)Learning in high-dimensional multimedia dataMultimedia Systems10.1007/s00530-015-0494-123:3(303-313)Online publication date: 1-Jun-2017
    • (2016)Low-Rank Feature Reduction and Sample Selection for Multi-output RegressionAdvanced Data Mining and Applications10.1007/978-3-319-49586-6_9(126-141)Online publication date: 13-Nov-2016
    • (2016)Unsupervised Hypergraph Feature Selection with Low-Rank and Self-Representation ConstraintsAdvanced Data Mining and Applications10.1007/978-3-319-49586-6_12(172-187)Online publication date: 13-Nov-2016

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    Figures

    Tables

    Media

    Share

    Share

    Share this Publication link

    Share on social media