On the set of images modulo viewpoint and contrast changes

By Ganesh Sundaramoorthi, Peter Petersen, V. Varadarajan, Stefano Soatto. 2009

58 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Towards a Definition of Disentangled Representations (2018, background): “Much of the research on perception and representation learning, especially in object recognition, has followed Gibson and his contemporaries in emphasising features which are invariant to transformations like pose or illumination [56, 22, 71, 49].”
Emergence of Invariance and Disentanglement in Deep Representations (2017, background): “Anselmi et al. (2016) develop a theory of invariance to locally compact groups, and aim to construct maximal (“distinctive”) invariants, like Sundaramoorthi et al. (2009) that, however, assume nuisances to be inﬁnite-dimensional groups (Grenander, 1993).”
Emergence of invariance and disentangling in deep representations (2017, background): “Anselmi et al. (2016) develop a theory of invariance to locally compact groups, and aim to construct maximal (“distinctive”) invariants, like Sundaramoorthi et al. (2009) that, however, assume nuisances to be infinite-dimensional groups (Grenander, 1993).”
The Invariance Hypothesis Implies Domain-Specific Regions in Visual Cortex (2014, result): “It is broadly in accord with other recent perspectives on the ventral stream and the problem of object recognition [38, 22].”
Visual Representations: Defining Properties and Deep Approximations (2014, methodology): “Similarly, Sundaramoorthi et al. (2009) have shown that maximal invariants can be constructed even for diffeomorphisms, which are infinitedimensional and non-compact.”
Mathematics of Deep Learning (2017, background): “Indeed, most of the variability in imaging data can be ascribed to the effects of illumination and viewpoint, quotienting out which leaves a thin set [79].”
Information Dropout: learning optimal representations through noise (2017, background): “…are maximally invariant to nuisances, especially when they have the structure of a (possibly inﬁnite-dimensional) group acting on the data, like Sundaramoorthi et al. (2009), or, when the nuisance is a locally compact group acting on each layer, by successive approximations implemented by…”
A Separation Principle for Control in the Age of Deep Learning (2017, background): “Similarly, the classical use of invariants in image analysis is to remove redundancy from the data by mapping it to the quotient space, which for image can be a thin set [37].”