Abstract
We are interested in the detection and segmentation of anomalies in images where the anomalies are typically small (i.e., a small tear in woven fabric, broken pin of an IC chip). From a statistical learning point of view, anomalies have low occurrence probability and are not from the main modes of a data distribution. Learning a generative model of anomalous data from a natural distribution of data can be difficult because the data distribution is heavily skewed towards a large amount of non-anomalous data. When training a generative model on such imbalanced data using an iterative learning algorithm like stochastic gradient descent (SGD), we observe an expected yet interesting trend in the loss values (a measure of the learned models performance) after each gradient update across data samples. Naturally, as the model sees more non-anomalous data during training, the loss values over a non-anomalous data sample decreases, while the loss values on an anomalous data sample fluctuates. In this work, our key hypothesis is that this change in loss values during training can be used as a feature to identify anomalous data. In particular, we propose a novel semi-supervised learning algorithm for anomaly detection and segmentation using an anomaly classifier that uses as input the loss profile of a data sample processed through an autoencoder. The loss profile is defined as a sequence of reconstruction loss values produced during iterative training. To amplify the difference in loss profiles between anomalous and non-anomalous data, we also introduce a Reinforcement Learning based meta-algorithm, which we call the neural batch sampler, to strategically sample training batches during autoencoder training. Experimental results on multiple datasets with a high diversity of textures and objects, often with multiple modes of defects within them, demonstrate the capabilities and effectiveness of our method when compared with existing state-of-the-art baselines.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
To be more precise, this should be written as \(R_{pred,\,t}\), but we omit the subscript t in the paper for simplicity.
References
Baur, C., Wiestler, B., Albarqouni, S., Navab, N.: Deep autoencoding models for unsupervised anomaly segmentation in brain MR images. In: Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries-4th International Workshop (2018)
Bengio, S., Vinyals, O., Jaitly, N., Shazeer, N.: Scheduled sampling for sequence prediction with recurrent neural networks. In: Cortes, C., Lawrence, N.D., Lee, D.D., Sugiyama, M., Garnett, R. (eds.) Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems (NIPS) (2015)
Bergmann, P., Fauser, M., Sattlegger, D., Steger, C.: Mvtec AD-A comprehensive real-world dataset for unsupervised anomaly detection. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2019)
Bergmann, P., Löwe, S., Fauser, M., Sattlegger, D., Steger, C.: Improving unsupervised defect segmentation by applying structural similarity to autoencoders. In: Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2019, vol. 5: VISAPP (2019)
Böttger, T., Ulrich, M.: Real-time texture error detection on textured surfaces with compressed sensing. Pattern Recogn. Image Anal. 26(1), 88–94 (2016). https://doi.org/10.1134/S1054661816010053
Carrera, D., Manganini, F., Boracchi, G., Lanzarone, E.: Defect detection in SEM images of nanofibrous materials. IEEE Trans. Ind. Inf. 13, 551 (2017)
Chen, L., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834–848 (2018)
Cui, L., Qi, Z., Chen, Z., Meng, F., Shi, Y.: Pavement distress detection using random decision forests. In: Zhang, C., et al. (eds.) ICDS 2015. LNCS, vol. 9208, pp. 95–102. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24474-7_14
Deng, J., Dong, W., Socher, R., Li, L., Li, K., Li, F.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (2009)
Eskin, E.: Anomaly detection over noisy data using learned probability distributions. In: Proceedings of the Seventeenth International Conference on Machine Learning (ICML) (2000)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2016)
Krähenbühl, P., Koltun, V.: Efficient inference in fully connected CRFS with gaussian edge potentials. In: Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems (NIPS) (2011)
Markou, M., Singh, S.: Novelty detection: a review—part 1: statistical approaches. Signal Process. 83(12), 2481–2497 (2003)
Napoletano, P., Piccoli, F., Schettini, R.: Anomaly detection in nanofibrous materials by CNN-based self-similarity. Sensors 18, 209 (2018)
Rahmani, M., Atia, G.K.: Coherence pursuit: fast, simple, and robust principal component analysis. IEEE Trans. Signal Process. 65(23), 6260–6275 (2017)
Ravanbakhsh, M., Sangineto, E., Nabi, M., Sebe, N.: Training adversarial discriminators for cross-channel abnormal event detection in crowds. In: IEEE Winter Conference on Applications of Computer Vision, WACV (2019)
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Ross, S., Gordon, G., Bagnell, D.: A reduction of imitation learning and structured prediction to no-regret online learning. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, pp. 627–635 (2011)
Ruff, L., et al.: Deep semi-supervised anomaly detection (2020)
Sabokrou, M., Khalooei, M., Fathy, M., Adeli, E.: Adversarially learned one-class classifier for novelty detection. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2018)
Schlegl, T., Seeböck, P., Waldstein, S.M., Schmidt-Erfurth, U., Langs, G.: Unsupervised anomaly detection with generative adversarial networks to guide marker discovery. In: Information Processing in Medical Imaging-25th International Conference, IPMI (2017)
Shelhamer, E., Long, J., Darrell, T.: Fully convolutional networks for semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(4), 640–651 (2017)
Shi, Y., Cui, L., Qi, Z., Meng, F., Chen, Z.: Automatic road crack detection using random structured forests. IEEE Trans. Intell. Transp. Syst. 17(12), 3434–3445 (2016)
Steger, C., Ulrich, M., Wiedemann, C.: Machine Vision Algorithms and Applications. John Wiley & Sons, Hoboken (2018)
Sutton, R.S., Barto, A.G.: Reinforcement learning-an introduction. In: Adaptive Computation and Machine Learning MIT Press, New York (1998)
Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8, 229–256 (1992)
Xu, H., Caramanis, C., Sanghavi, S.: Robust PCA via outlier pursuit. In: Advances in Neural Information Processing Systems 23: 24th Annual Conference on Neural Information Processing Systems (NIPS) (2010)
Yamanishi, K., Takeuchi, J.I., Williams, G., Milne, P.: On-line unsupervised outlier detection using finite mixtures with discounting learning algorithms. Data Min. Knowl. Disc. 8(3), 275–300 (2004)
Acknowledgements
This research is supported with funding from Shimizu Corporation.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Chu, WH., Kitani, K.M. (2020). Neural Batch Sampling with Reinforcement Learning for Semi-supervised Anomaly Detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12371. Springer, Cham. https://doi.org/10.1007/978-3-030-58574-7_45
Download citation
DOI: https://doi.org/10.1007/978-3-030-58574-7_45
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58573-0
Online ISBN: 978-3-030-58574-7
eBook Packages: Computer ScienceComputer Science (R0)