Abstract
Computer vision systems for automatic image categorization have become accurate and reliable enough that they can run continuously for days or even years as components of real-world commercial applications. A major open problem in this context, however, is quality control. Good classification performance can only be expected if systems run under the specific conditions, in particular data distributions, that they were trained for. Surprisingly, none of the currently used deep network architectures have a built-in functionality that could detect if a network operates on data from a distribution it was not trained for, such that potentially a warning to the human users could be triggered.
In this work, we describe KS(conf), a procedure for detecting such outside of specifications (out-of-specs) operation, based on statistical testing of the network outputs. We show by extensive experiments using the ImageNet, AwA2 and DAVIS datasets on a variety of ConvNets architectures that KS(conf) reliably detects out-of-specs situations. It furthermore has a number of properties that make it a promising candidate for practical deployment: it is easy to implement, adds almost no overhead to the system, works with all networks, including pretrained ones, and requires no a priori knowledge of how the data distribution could change.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
We use the pretrained models from https://github.com/taehoonlee/tensornets.
References
Bansal, A., Farhadi, A., Parikh, D.: Towards transparent systems: semantic characterization of failure modes. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 366–381. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10599-4_24
Ben-David, S., Blitzer, J., Crammer, K., Kulesza, A., Pereira, F., Vaughan, J.W.: A theory of learning from different domains. Mach. Learn. 79(1–2), 151–175 (2010)
Bendale, A., Boult, T.: Towards open world recognition. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2015)
Bendale, A., Boult, T.: Towards open set deep networks. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
Daftry, S., Zeng, S., Bagnell, J.A., Hebert, M.: Introspective perception: learning to predict failures in vision systems. In: International Conference on Intelligent Robots (IROS) (2016)
Dunning, T., Ertl, O.: Computing extremely accurate quantiles using t-digests (2014). github.com
Ganin, Y., Lempitsky, V.: Unsupervised domain adaptation by backpropagation. In: International Conference on Machine Learing (ICML) (2015)
Guo, C., Pleiss, G., Sun, Y., Weinberger, K.Q.: On calibration of modern neural networks. In: International Conference on Machine Learing (ICML) (2017)
Harel, M., Mannor, S., El-Yaniv, R., Crammer, K.: Concept drift detection through resampling. In: International Conference on Machine Learning (ICML) (2014)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
Howard, A.G., et al.: Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv:1704.04861 (2017)
Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., Keutzer, K.: SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and \({<}\)0.5 MB model size. arXiv:1602.07360 (2016)
Jain, L.P., Scheirer, W.J., Boult, T.E.: Multi-class open set recognition using probability of inclusion. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8691, pp. 393–409. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10578-9_26
Kuncheva, L.I., Faithfull, W.J.: PCA feature extraction for change detection in multidimensional unlabeled data. IEEE Trans. Neural Netw. (T-NN) 25(1), 69–80 (2014)
Marsaglia, G., Tsang, W.W., Wang, J.: Evaluating Kolmogorov’s distribution. J. Stat. Softw. Articles 8(18), 1–4 (2003)
Massey Jr., F.J.: The Kolmogorov-Smirnov test for goodness of fit. J. Am. Stat. Assoc. 46(253), 68–78 (1951)
Perazzi, F., Pont-Tuset, J., McWilliams, B., Van Gool, L., Gross, M., Sorkine-Hornung, A.: A benchmark dataset and evaluation methodology for video object segmentation. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
Platt, J.: Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. In: Advances in Large Margin Classifiers. Cambridge University Press (1999)
Rebuffi, S.A., Kolesnikov, A., Sperl, G., Lampert, C.H.: iCaRL: incremental classifier and representation learning. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
dos Reis, D.M., Flach, P., Matwin, S., Batista, G.: Fast unsupervised online drift detection using incremental Kolmogorov-Smirnov test. In: SIGKDD (2016)
Royer, A., Lampert, C.H.: Classifier adaptation at prediction time. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2015)
Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. (IJCV) 115(3), 211–252 (2015)
Sethi, T.S., Kantardzic, M., Hu, H.: A grid density based framework for classifying streaming data in the presence of concept drift. J. Intell. Inf. Syst. 46(1), 179–211 (2016)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556 (2014)
Sun, R., Lampert, C.H.: KS(conf): A light-weight test if a ConvNet operates outside of its specifications. arXiv:1804.04171 (2018)
Tange, O.: Gnu parallel - the command-line power tool. USENIX Mag. 36(1), 42–47 (2011). http://www.gnu.org/s/parallel
Wang, H., Abraham, Z.: Concept drift detection for streaming data. In: International Joint Conference on Neural Networks (IJCNN) (2015)
Xian, Y., Lampert, C.H., Schiele, B., Akata, Z.: Zero-shot learning - a comprehensive evaluation of the good, the bad and the ugly. IEEE Trans. Pattern Anal. Mach. Intell. (T-PAMI) (2018)
Zhang, P., Wang, J., Farhadi, A., Hebert, M., Parikh, D.: Predicting failures of vision systems. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2014)
Zliobaite, I.: Change with delayed labeling: when is it detectable? In: International Conference on Data Mining Workshops (2010)
Zoph, B., Vasudevan, V., Shlens, J., Le, Q.V.: Learning transferable architectures for scalable image recognition. arXiv:1707.07012 (2017)
Acknowledgments
This work was funded in parts by the European Research Council under the European Union’s Seventh Framework Programme (FP7/2007-2013)/ERC grant agreement no. 308036.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Sun, R., Lampert, C.H. (2019). KS(conf): A Light-Weight Test if a ConvNet Operates Outside of Its Specifications. In: Brox, T., Bruhn, A., Fritz, M. (eds) Pattern Recognition. GCPR 2018. Lecture Notes in Computer Science(), vol 11269. Springer, Cham. https://doi.org/10.1007/978-3-030-12939-2_18
Download citation
DOI: https://doi.org/10.1007/978-3-030-12939-2_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-12938-5
Online ISBN: 978-3-030-12939-2
eBook Packages: Computer ScienceComputer Science (R0)