Related Concepts
Definition
The term invariant methods in computer vision refers to a broad class of ideas for designing both representations and metrics that are invariant/robust to (and only to) nuisance factors in computer vision such as viewpoint, motion, defocus, etc. for different related modalities including images, videos, and point clouds.
Background
Computer vision consists of inferring geometric and semantic properties of objects and scenes, from 2D projections as seen through cameras. This theme appears in applications such as object recognition, localization, segmentation, 3D reconstruction, etc. As canonical examples, we will focus on object, scene, and action recognition. Usually, these tasks need to be performed given a single image of the object/scene or a video. That is, we usually do not have access to the full 3D structure of the object or scenes, but have 2D projections obtained using a camera. As such, a lot of...
References
Vedaldi A (2008) Invariant representations and learning for computer vision. Ph.D. thesis, Citeseer
Simard PY, LeCun YA, Denker JS, Victorri B (1998) Transformation invariance in pattern recognition-tangent distance and tangent propagation. In: Neural networks: tricks of the trade. Springer, pp 239–274
Werman M (2014) Affine invariants. Springer US, Boston, pp 20–22
Flusser J, Suk T (1993) Pattern recognition by affine moment invariants. Pattern Recognit 26(1):167–174
Lowe DG (2004) Distinctive image features from scale-invariant key points. Int J Comput Vis 60(2):91–110
Jaderberg M, Simonyan K, Zisserman A et al (2015) Spatial transformer networks. In: Advances in neural information processing systems, pp 2017–2025
Sabour S, Frosst N, Hinton GE (2017) Dynamic routing between capsules. In: Advances in neural information processing systems, pp 3856–3866
Srivastava A, Klassen EP (2016) Functional and shape data analysis. Springer, New York
Flusser J, Suk T, Boldyš J, Zitová B (2014) Projection operators and moment invariants to image blurring. IEEE Trans Pattern Anal Mach Intell 37(4):786–802
Zhang Z, Klassen E, Srivastava A, Turaga P, Chellappa R (2011) Blurring-invariant Riemannian metrics for comparing signals and images. In: 2011 international conference on computer vision, pp 1770–1775. IEEE
Gopalan R, Taheri S, Turaga P, Chellappa R (2012) A blur-robust descriptor with applications to face recognition. IEEE Trans Pattern Anal Mach Intell 34(6):1220–1226
Sakoe H, Chiba S (1978) Dynamic programming algorithm optimization for spoken word recognition. IEEE Trans Acoust Speech Signal Process 26(1): 43–49
Srivastava A, Klassen E, Joshi SH, Jermyn IH (2010) Shape analysis of elastic curves in Euclidean spaces. IEEE Trans Pattern Anal Mach Intell 33(7):1415–1428
Veeraraghavan A, Srivastava A, Roy-Chowdhury AK, Chellappa R (2009) Rate-invariant recognition of humans and their activities. IEEE Trans Image Process 18(6):1326–1339
Lohit S, Wang Q, Turaga P (2019) Temporal transformer networks: joint learning of invariant and discriminative time warping. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 12426–12435
Hallinan PW et al (1994) A low-dimensional representation of human faces for arbitrary lighting conditions. In: CVPR, vol 94, pp 995–999
Belhumeur PN, Kriegman DJ (1998) What is the set of images of an object under all possible illumination conditions? Int J Comput Vis 28(3):245–260
Basri R, Jacobs DW (2003) Lambertian reflectance and linear subspaces. IEEE Trans Pattern Anal Mach Intell 25:218–233
Lohit S, Turaga P (2017) Learning invariant Riemannian geometric representations using deep nets. In: Proceedings of the IEEE international conference on computer vision, pp 1329–1338
Qi CR, Su H, Mo K, Guibas LJ (2017) Pointnet: deep learning on point sets for 3d classification and segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 652–660
Reiss TH (ed) (1993) Invariance to projective transformations. Springer Berlin/Heidelberg, pp 101–114
Yu G, Morel J-M (2011) ASIFT: an algorithm for fully affine invariant comparison. Image Processing On Line 1:11–38
Dey TK, Mandal S, Varcho W (2017) Improved image classification using topological persistence. In: Vision, modeling & visualization, VMV 2017, Bonn, 25–27 Sept 2017, pp 161–168
Vemulapalli R, Arrate F, Chellappa R (2014) Human action recognition by representing 3D skeletons as points in a lie group. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 588–595
Chen H, Belhumeur P, Jacobs D (2000) In search of illumination invariants. In: Proceedings IEEE conference on computer vision and pattern recognition, CVPR 2000 (Cat. No. PR00662), vol 1. IEEE, pp 254–261
Ho J, Kriegman D (2005) On the effect of illumination and face recognition. In: In face processing: advanced modeling and methods. Citeseer
LeCun Y, Huang FJ, Bottou L (2004) Learning methods for generic object recognition with invariance to pose and lighting. In: Proceedings of the IEEE conference on computer vision and pattern recognition
Goodfellow I, Lee H, Le QV, Saxe A, Ng AY (2009) Measuring invariances in deep networks. In: Advances in neural information processing systems, pp 646–654
Erhan D, Courville A, Bengio Y (2010) Understanding representations learned in deep architectures. Technical Report
Fawzi A, Frossard P (2015) Manitest: are classifiers really invariant? In: British machine vision conference
Dodge S, Karam L (2016) Understanding how image quality affects deep neural networks. In: 2016 eighth international conference on quality of multimedia experience (QoMEX), pp 1–6. IEEE
Szegedy C, Zaremba W, Sutskever I, Bruna J, Erhan D, Goodfellow I, Fergus R (2014) Intriguing properties of neural networks. In: International conference on learning representations
Rifai S, Mesnil G, Vincent P, Muller X, Bengio Y, Dauphin Y, Glorot X (2011) Higher order contractive auto-encoder. In: Joint European conference on machine learning and knowledge discovery in databases. Springer, pp 645–660
Bruna J, Mallat S (2013) Invariant scattering convolution networks. IEEE Trans Pattern Anal Mach Intell 35(8):1872–1886
Xu Y, Xiao T, Zhang J, Yang K, Zhang Z (2014) Scale-invariant convolutional neural networks. arXiv preprint arXiv:1411.6369
Kulkarni TD, Whitney WF, Kohli P, Tenenbaum J (2015) Deep convolutional inverse graphics network. In: Advances in neural information processing systems, pp 2539–2547
Kim H, Mnih A (2018) Disentangling by factorising. In: International conference on machine learning, pp 2654–2663
Shu Z, Sahasrabudhe M, R. Alp Guler, Samaras D, Paragios N, Kokkinos I (2018) Deforming autoencoders: unsupervised disentangling of shape and appearance. In: Proceedings of the European conference on computer vision (ECCV), pp 650–665
Koneripalli K, Lohit S, Anirudh R, Turaga P (2020) Rate-invariant autoencoding of time-series. In: IEEE international conference on acoustics, speech and signal processing (ICASSP)
Shukla A, Bhagat S, Uppal S, Anand S, Turaga P. Product of orthogonal spheres parameterization for disentangled representation learning. In: British machine vision conference (2019)
Author information
Authors and Affiliations
Corresponding author
Section Editor information
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this entry
Cite this entry
Lohit, S., Turaga, P., Veeraraghavan, A. (2020). Invariant Methods in Computer Vision. In: Computer Vision. Springer, Cham. https://doi.org/10.1007/978-3-030-03243-2_826-1
Download citation
DOI: https://doi.org/10.1007/978-3-030-03243-2_826-1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-03243-2
Online ISBN: 978-3-030-03243-2
eBook Packages: Springer Reference Computer SciencesReference Module Computer Science and Engineering