Abstract
In this paper, we employ anomaly detection methods to enhance the ability of object detectors by using the context of their detections. This has numerous potential applications from boosting the performance of standard object detectors, to the preliminary validation of annotation quality, and even for robotic exploration and object search. We build our method on autoencoder networks for detecting anomalies, where we do not try to filter incoming data based on anomality score as is usual, but instead, we focus on the individual features of the data representing an actual scene. We show that one can teach autoencoders about the contextual relationship of objects in images, i.e. the likelihood of co-detecting classes in the same scene. This can then be used to identify detections that do and do not fit with the rest of the current observations in the scene. We show that the use of this information yields better results than using traditional thresholding when deciding if weaker detections are actually classed as observed or not. The experiments performed not only show that our method significantly improves the performance of CNN object detectors, but that it can be used as an efficient tool to discover incorrectly-annotated images.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
An, J., Cho, S.: Variational autoencoder based anomaly detection using reconstruction probability. Spec. Lect. IE 2(1), 1–18 (2015)
Bell, S., Lawrence Zitnick, C., Bala, K., Girshick, R.: Inside-outside net: detecting objects in context with skip pooling and recurrent neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2874–2883 (2016)
Biederman, I.: Recognition-by-components: a theory of human image understanding. Psychol. Rev. 94(2), 115 (1987)
Bishop, C.M.: Pattern Recognition and Machine Learning. Information Science and Statistics. Springer, New York (2006)
Board, T.N.T.S.: Collision between vehicle controlled by developmental automated driving system and pedestrian, Tempe, Arizona, p. 78, 18 March 2018
Chen, X., Gupta, A.: Spatial memory for context reasoning in object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4086–4096 (2017)
Creswell, A., Arulkumaran, K., Bharath, A.A.: On denoising autoencoders trained to minimise binary cross-entropy. arXiv:1708.08487 [cs, stat] October 2017
Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255. IEEE (2009)
Divvala, S.K., Hoiem, D., Hays, J.H., Efros, A.A., Hebert, M.: An empirical study of context in object detection. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1271–1278. IEEE (2009)
Dutta, A., Zisserman, A.: The VGG image annotator (via). arXiv preprint arXiv:1904.10699 (2019)
Galleguillos, C., Belongie, S.: Context based object categorization: a critical survey. Comput. Vis. Image Understand. 114(6), 712–722 (2010)
Gehring, J., Miao, Y., Metze, F., Waibel, A.: Extracting deep bottleneck features using stacked auto-encoders. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 3377–3381, May 2013. DOIurl10.1109/ICASSP.2013.6638284. ISSN: 2379-190X
George Broughton, J.B.: Auto image anomaly (2020). https://github.com/broughtong/Auto-Image-Anomaly
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Hu, H., Gu, J., Zhang, Z., Dai, J., Wei, Y.: Relation networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3588–3597 (2018)
Kramer, M.A.: Nonlinear principal component analysis using autoassociative neural networks. AIChE J. 37(2), 233–243 (1991). https://doi.org/10.1002/aic.690370209. https://aiche.onlinelibrary.wiley.com/doi/abs/10.1002/aic.690370209
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)
Lin, T.Y., et al.: Microsoft COCO: common objects in context. arXiv:1405.0312 [cs] February 2015
Lin, T.-Y.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740–755. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_48
Liu, Y., Wang, R., Shan, S., Chen, X.: Structure inference net: object detection using scene-level context and instance-level relationships. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6985–6994 (2018)
Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779–788 (2016)
Sakurada, M., Yairi, T.: Anomaly detection using autoencoders with nonlinear dimensionality reduction. In: Proceedings of the MLSDA 2014 2nd Workshop on Machine Learning for Sensory Data Analysis, p. 4. ACM (2014)
Sakurada, M., Yairi, T.: Anomaly detection using autoencoders with nonlinear dimensionality reduction. In: Proceedings of the MLSDA 2014 2nd Workshop on Machine Learning for Sensory Data Analysis - MLSDA 2014, Gold Coast, Australia QLD, Australia, pp. 4–11. ACM Press (2014). https://doi.org/10.1145/2689746.2689747. http://dl.acm.org/citation.cfm?doid=2689746.2689747
Santos, J.M., Krajník, T., Fentanes, J.P., Duckett, T.: Lifelong information-driven exploration to complete and refine 4-d spatio-temporal maps. IEEE Robot. Autom. Lett. 1(2), 684–691 (2016). https://doi.org/10.1109/LRA.2016.2516594
Santos, J.M., Krajník, T., Duckett, T.: Spatio-temporal exploration strategies for long-term autonomy of mobile robots. Robot. Auton. Syst. 88(C), 116–126 (2017)
Shrivastava, A., Gupta, A.: Contextual priming and feedback for faster R-CNN. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 330–348. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46448-0_20
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9 (2015)
Vincent, P., Larochelle, H., Bengio, Y., Manzagol, P.A.: Extracting and composing robust features with denoising autoencoders. In: Proceedings of the 25th International Conference on Machine Learning - ICML 2008, Helsinki, Finland, pp. 1096–1103. ACM Press (2008). https://doi.org/10.1145/1390156.1390294. http://portal.acm.org/citation.cfm?doid=1390156.1390294
Zeiler, M.D.: ADADELTA: an adaptive learning rate method. arXiv:1212.5701 [cs] December 2012
Zhao, R., Ouyang, W., Li, H., Wang, X.: Saliency detection by multi-context deep learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1265–1274 (2015)
Zhou, C., Paffenroth, R.C.: Anomaly detection with robust deep autoencoders. In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD 2017, Halifax, NS, Canada, pp. 665–674. ACM Press (2017). https://doi.org/10.1145/3097983.3098052. http://dl.acm.org/citation.cfm?doid=3097983.3098052
Zhou, C., Paffenroth, R.C.: Anomaly detection with robust deep autoencoders. In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 665–674. ACM (2017)
Zhu, Y., Urtasun, R., Salakhutdinov, R., Fidler, S.: segDeepM: exploiting segmentation and context in deep neural networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4703–4711 (2015)
Zong, B., et al.: Deep autoencoding gaussian mixture model for unsupervised anomaly detection (2018)
Acknoledgement
The authors acknowledge the support of the Czech Science Foundation project “Towards long-term autonomy through introduction of the temporal domain into spatial representations used in robotics “20-27034J”. The calculations were performed using computational resources provided by the OP VVV MEYS funded project CZ.02.1.01/0.0/0.0/16_019/0000765 “Research Center for Informatics”.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Blaha, J., Broughton, G., Krajník, T. (2021). Boosting the Performance of Object Detection CNNs with Context-Based Anomaly Detection. In: Gao, H., Wang, X., Iqbal, M., Yin, Y., Yin, J., Gu, N. (eds) Collaborative Computing: Networking, Applications and Worksharing. CollaborateCom 2020. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 349. Springer, Cham. https://doi.org/10.1007/978-3-030-67537-0_11
Download citation
DOI: https://doi.org/10.1007/978-3-030-67537-0_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-67536-3
Online ISBN: 978-3-030-67537-0
eBook Packages: Computer ScienceComputer Science (R0)