Fetching the paper…
Reading the bibliography…
Visual representations are defined in terms of minimal sufficient statistics of visual data, for a class of tasks, that are also invariant to nuisance variability.
Sufficiency and statistical decision functions
Bahadur, R. R · 1954
Earlier work this paper cites.
Predictive likelihood
Hinkley, D · 1979
Earlier work this paper cites.
A bayes but not classically sufficient statistic
Blackwell, D. and Ramamoorthi, R.V · 1982
Earlier work this paper cites.
Probability and statistics
DeGroot, M. H · 1989
Earlier work this paper cites.
Elements of Information Theory
Cover, T. M. and Thomas, J. A · 1991
Earlier work this paper cites.
Axioms and fundamental equations of image processing
Alvarez, L., Guichard, F., Lions, P. L., and Morel, J. M · 1993
Earlier work this paper cites.
General Pattern Theory
Grenander, U · 1993
Earlier work this paper cites.
Mathematical Statistics
Shao, J · 1998
Earlier work this paper cites.
Statistics of natural images and models
Huang, J. and Mumford, D · 1999
Earlier work this paper cites.
The information bottleneck method
Tishby, N., Pereira, F. C., and Bialek, W · 2000
Earlier work this paper cites.
In all likelihood: Statistical modeling and inference using likelihood
Pawitan, Y · 2001
Earlier work this paper cites.
Distinctive image features from scale-invariant keypoints
Lowe, D. G · 2004
Earlier work this paper cites.
A comparison of affine region detectors
Mikolajczyk, K., Tuytelaars, T., Schmid, C., Zisserman, A., Matas, J., Schaffalitzky, F., Kadir, T., and Gool, L. Van · 2004
Cited alongside, same era.
Minimal sufficient statistics emerge from the observed likelihood function
Fraser, D. and Naderi, A · 2007
Cited alongside, same era.
Unsupervised learning of invariant feature hierarchies with applications to object recognition
Ranzato, M., Huang, F. J., Boureau, Y.-L., and LeCun, Y · 2007
Cited alongside, same era.
A feedforward architecture accounts for rapid categorization
Serre, T., Oliva, A., and Poggio, T · 2007
Cited alongside, same era.
Learning deep architectures for ai
Bengio, Y · 2009
Cited alongside, same era.
On invariance in hierarchical models
Bouvrie, J. V., Rosasco, L., and Poggio, T · 2009
Cited alongside, same era.
Diffusion runs low on persistence fast
Chen, C. and Edelsbrunner, H · 2011
Later among the works it cites.
Is sift scale invariant?
Morel, J. M. and Yu, G · 2011
Later among the works it cites.
Modeling the joint density of two images under a variety of transformations
Susskind, J., Memisevic, R., Hinton, G. E., and Pollefeys, M · 2011
Later among the works it cites.
Learning invariant feature hierarchies
LeCun, Y · 2012
Later among the works it cites.
Machine Learning for Computer Vision , chapter Visual Correspondence, the Lambert-Ambient Shape Space and the Systematic Design of Feature Descriptors
Dong, J. and Soatto, S · 2014
Closest in time.
Multi-scale orderless pooling of deep convolutional activation features
Gong, Y., Wang, L., Guo, R., and Lazebnik, S · 2014
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Past-future information bottleneck in dynamical systems
Creutzig, F., Globerson, A., and Tishby, N · 2009
Cited alongside, same era.
Actionable information in vision
Soatto, S · 2009
Cited alongside, same era.
On the set of images modulo viewpoint and contrast changes
Sundaramoorthi, G., Petersen, P., Varadarajan, V. S., and Soatto, S · 2009
Cited alongside, same era.
A theoretical analysis of feature pooling in visual recognition
Boureau, Y.-L., Ponce, J., and LeCun, Y · 2010
Cited alongside, same era.
Classification with scattering operators
Bruna, J. and Mallat, S · 2011
Cited alongside, same era.
The devil is in the details: an evaluation of recent feature encoding methods
Chatfield, K., Lempitsky, V., Vedaldi, A., and Zisserman, A · 2011
Cited alongside, same era.
Closest in time.
Learning local feature descriptors using convex optimisation
Simonyan, K., Vedaldi, A., and Zisserman, A · 2014
Closest in time.
On invariance and selectivity in representation learning
Anselmi, F., Rosasco, L., and Poggio, T · 2015
Closest in time.
Domain size pooling in local descriptors: Dsp-sift
Dong, J. and Soatto, S · 2015
Closest in time.
Automatic thresholding of SIFT descriptors
Kirchner, M. R · 2015
Closest in time.
A probabilistic theory of deep learning
Patel, A., Nguyen, T., and Baraniuk, R · 2015
Closest in time.
Maximally informative hierarchical representations of high-dimensional data
Ver Steeg, G. and Galstyan, A · 2015
Closest in time.