Results 1  10
of
27
Representation learning: A review and new perspectives.
 of IEEE Conf. Comp. Vision Pattern Recog. (CVPR),
, 2005
"... AbstractThe success of machine learning algorithms generally depends on data representation, and we hypothesize that this is because different representations can entangle and hide more or less the different explanatory factors of variation behind the data. Although specific domain knowledge can b ..."
Abstract

Cited by 173 (4 self)
 Add to MetaCart
AbstractThe success of machine learning algorithms generally depends on data representation, and we hypothesize that this is because different representations can entangle and hide more or less the different explanatory factors of variation behind the data. Although specific domain knowledge can be used to help design representations, learning with generic priors can also be used, and the quest for AI is motivating the design of more powerful representationlearning algorithms implementing such priors. This paper reviews recent work in the area of unsupervised feature learning and deep learning, covering advances in probabilistic models, autoencoders, manifold learning, and deep networks. This motivates longer term unanswered questions about the appropriate objectives for learning good representations, for computing representations (i.e., inference), and the geometrical connections between representation learning, density estimation, and manifold learning.
1 Invariant Scattering Convolution Networks
, 1203
"... Abstract—A wavelet scattering network computes a translation invariant image representation, which is stable to deformations and preserves high frequency information for classification. It cascades wavelet transform convolutions with nonlinear modulus and averaging operators. The first network laye ..."
Abstract

Cited by 44 (7 self)
 Add to MetaCart
(Show Context)
Abstract—A wavelet scattering network computes a translation invariant image representation, which is stable to deformations and preserves high frequency information for classification. It cascades wavelet transform convolutions with nonlinear modulus and averaging operators. The first network layer outputs SIFTtype descriptors whereas the next layers provide complementary invariant information which improves classification. The mathematical analysis of wavelet scattering networks explain important properties of deep convolution networks for classification. A scattering representation of stationary processes incorporates higher order moments and can thus discriminate textures having same Fourier power spectrum. State of the art classification results are obtained for handwritten digits and texture discrimination, with a Gaussian kernel SVM and a generative PCA classifier. 1
The computational magic of the ventral stream: sketch of a theory (and why some deep architectures work).
, 2012
"... ..."
Intermittent Process Analysis with Scattering Moments”, submitted to Annals of Statistics
, 2013
"... ar ..."
(Show Context)
Matching through features and features through matching. arXiv preprint arXiv:1211.4771
, 2012
"... This paper addresses how to construct features for the problem of image correspondence, in particular, the paper addresses how to construct features so as to maintain the right level of invariance versus discriminability. We show that without additional prior knowledge of the 3D scene, the right tra ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
(Show Context)
This paper addresses how to construct features for the problem of image correspondence, in particular, the paper addresses how to construct features so as to maintain the right level of invariance versus discriminability. We show that without additional prior knowledge of the 3D scene, the right tradeoff cannot be established in a preprocessing step of the images as is typically done in most featurebased matching methods. However, given knowledge of the second image to match, the tradeoff between invariance and discriminability of features in the first image is less ambiguous. This suggests to setup the problem of feature extraction and matching as a joint estimation problem. We develop a possible mathematical framework, a possible computational algorithm, and we give example demonstration on finding correspondence on images related by a scene that undergoes large 3D deformation of nonplanar objects and camera viewpoint change. I.
Leftinvariant evolutions of wavelet transforms on the similitude group
, 2013
"... Enhancement of multiplescale elongated structures in noisy image data is relevant for many biomedical applications but commonly used PDEbased enhancement techniques often fail at crossings in an image. To get an overview of how an image is composed of local multiplescale elongated structures we ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
(Show Context)
Enhancement of multiplescale elongated structures in noisy image data is relevant for many biomedical applications but commonly used PDEbased enhancement techniques often fail at crossings in an image. To get an overview of how an image is composed of local multiplescale elongated structures we construct a multiple scale orientation score, which is a continuous wavelet transform on the similitude group, SIM(2). Our unitary transform maps the space of images onto a reproducing kernel space defined on SIM(2), allowing us to robustly relate Euclidean (and scaling) invariant operators on images to leftinvariant operators on the corresponding continuous wavelet transform. Rather than often used wavelet (soft)thresholding techniques, we employ the group structure in the wavelet domain to arrive at leftinvariant evolutions and flows (diffusion), for contextual crossing preserving enhancement of multiple scale elongated structures in noisy images. We present experiments that display benefits of our work compared to recent PDE techniques acting directly on the images and to our previous work on leftinvariant diffusions on orientation scores defined on Euclidean motion group.
Representations in Visual Cortex (and in Deep Learning Architectures)
, 2011
"... a theory of deep hierarchical architectures ..."
(Show Context)
massachusetts institute of technology, cambridge, ma 02139 usa — www.csail.mit.eduDoes invariant recognition predict tuning of neurons in sensory cortex?
, 2013
"... Does invariant recognition predict tuning of neurons in sensory cortex? ..."
(Show Context)