CoChat
Sign Up
Cited by 399Anomaly Detection Techniques and ApplicationsDomain Adaptation and Few-Shot LearningAdvanced Neural Network Applications

Learning Deep Features for One-Class Classification

Open access
Perera, Pramuditha, Patel, Vishal M.·2019·IEEE Transactions on Image Processing
DOI 10.1109/tip.2019.2917862
Open this paper in CoChat — free accountOpen PDF

Abstract

We present a novel deep-learning-based approach for one-class transfer learning in which labeled data from an unrelated task is used for feature learning in one-class classification. The proposed method operates on top of a convolutional neural network (CNN) of choice and produces descriptive features while maintaining a low intra-class variance in the feature space for the given class. For this purpose two loss functions, compactness loss and descriptiveness loss, are proposed along with a parallel CNN architecture. A template matching-based framework is introduced to facilitate the testing process. Extensive experiments on publicly available anomaly detection, novelty detection, and mobile active authentication datasets show that the proposed deep one-class (DOC) classification method achieves significant improvements over the state-of-the-art.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/tip.2019.2917862

Cites

35 of 35 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 13

  1. [1][1] D. Abati, A. Porrello, S. Calderara, and R. Cucchiara. AND: Autoregressive Novelty Detectors. ArXiv e-prints , 2018. -
  2. [5][5] R. Chalapathy, A. K. Menon, and S. Chawla. Anomaly detection using one-class neural networks. CoRR , 2018. -
  3. [20][20] D. P. Kingma and M. Welling. Auto-encoding variational bayes. In International Conference on Learning Representations . -
  4. [22][22] A. Krizhevsky, I. Sutskever, and G. E. Hinton. Imagenet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems 25 , pages 1097-1105, 2012. -
  5. [31][31] P. Perera, R. Nallapati, and B. Xiang. Ocgan: One-class novelty detection using gans with constrained latent representations. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , June 2019. -
  6. [32][32] P. Perera and V. M. Patel. Dual-minimax prob-ability machines for oneclass mobile active authentication. In IEEE Conference on Biometrics: Theory, Applications,and Systems (BTAS) , September 2018. -
  7. [34][34] P. Perera and V. M. Patel. Deep transfer learning for multiple class novelty detection. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , June 2019. -
  8. [38][38] E. Rodner, B. Barz, Y. Guanche, M. Flach, M. D. Mahecha, P. Bodesheim, M. Reichstein, and J. Denzler. Maximally divergent intervals for anomaly detection. CoRR , abs/1610.06761, 2016. - · arXiv
  9. [39][39] E. Rodner, E. sabrina Wacker, M. Kemmler, and J. Denzler. Oneclass classification for anomaly detection in wire ropes with gaussian processes in a few lines of code. In In: Conference on Machine Vision Applications (MVA) , pages 219-222, 2011. -
  10. [40][40] L. Ruff, R. Vandermeulen, N. Goernitz, L. Deecke, S. A. Siddiqui, A. Binder, E. M¨ uller, and M. Kloft. Deep one-class classification. In Proceedings of the 35th International Conference on Machine Learning , pages 4393-4402, 2018. -
  11. [44][44] K. Simonyan and A. Zisserman. Very deep convolutional networks for large-scale image recognition. CoRR , 2014. -
  12. [46][46] L. van der Maaten and G. E. Hinton. Visualizing high-dimensional data using t-sne. Journal of Machine Learning Research , 9:2579-2605, 2008. -
  13. [48][48] P. Vincent, H. Larochelle, I. Lajoie, Y. Bengio, and P.-A. Manzagol. Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion. Journal of Machine Learning Research , 11:3371-3408, 2010. -

Cited by

Sorted by citations

Authors
Perera, P., & Patel, V. M.
Affiliations
Johns Hopkins University (US)
ORCID
Venue
IEEE Transactions on Image Processing
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Published
2019-11
Volume
28
Issue
11
Pages
5450-5463
ISSN
  • 1057-7149 (ISSN-L)
  • 1941-0042
DOI
10.1109/tip.2019.2917862
OpenAlex
W2783748519
Cited by
399
References
35
Citations by year
2026: 20 · 2025: 39 · 2024: 36 · 2023: 58 · 2022: 67 · 2021: 88 · 2020: 51 · 2019: 35 · 2018: 5
FWCI
27.19
Type
journal article
Language
en
Open access
Licence
Locations
  • IEEE Transactions on Image Processing (publishedVersion)
  • PubMed (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Funders
Office of Naval Research Global (YIP N00014-16-1-3134)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Anomaly Detection Techniques and Applications
  • Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
Keywords
one-class classification, transfer learning, representation learning, template matching, anomaly detection, novelty detection, parallel convolutional neural network

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review