Transformation Equivariant Boltzmann Machines

Kivinen, Jyri; Williams, Christopher K. I.

doi:10.1007/978-3-642-21735-7_1

Cited by 46 publications

(29 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Pooling is the use of summary statistics of adjacent outputs in a feature map to determine the activations to be propagated to the subsequent layer. It results in rotationally and translationally invariant features [34]. For a window of size × , average pooling returns the arithmetic mean of signals in the window whereas maxpooling returns the dominant signal in that window.…”

Section: Cnn Building Blocksmentioning

confidence: 99%

See 1 more Smart Citation

Detection of Informal Settlements from VHR Images Using Convolutional Neural Networks

et al. 2017

View full text Add to dashboard Cite

Information about the location and extent of informal settlements is necessary to guide decision making and resource allocation for their upgrading. Very high resolution (VHR) satellite images can provide this useful information, however, different urban settlement types are hard to be automatically discriminated and extracted from VHR imagery, because of their abstract semantic class definition. State-of-the-art classification techniques rely on hand-engineering spatial-contextual features to improve the classification results of pixel-based methods. In this paper, we propose to use convolutional neural networks (CNNs) for learning discriminative spatial features, and perform automatic detection of informal settlements. The experimental analysis is carried out on a QuickBird image acquired over Dar es Salaam, Tanzania. The proposed technique is compared against support vector machines (SVMs) using texture features extracted from grey level co-occurrence matrix (GLCM) and local binary patterns (LBP), which result in accuracies of 86.65% and 90.48%, respectively. CNN leads to better classification, resulting in an overall accuracy of 91.71%. A sensitivity analysis shows that deeper networks result in higher accuracies when large training sets are used. The study concludes that training CNN in an end-to-end fashion can automatically learn spatial features from the data that are capable of discriminating complex urban land use classes.

show abstract

Section: Cnn Building Blocksmentioning

confidence: 99%

“…It results in rotationally and translationally invariant features [34]. For a window of size p × p, average pooling returns the arithmetic mean of signals in the window whereas maxpooling returns the dominant signal in that window.…”

Section: Cnn Building Blocksmentioning

confidence: 99%

Detection of Informal Settlements from VHR Images Using Convolutional Neural Networks

et al. 2017

View full text Add to dashboard Cite

show abstract

“…Current approaches do not address the problem of rotation-invariance directly, but use a predefined set of transformations to transform either the input images [19,21] or the learned filters [13,20]. We were inspired by these approaches to modify the RBM learning process, such that to learn invariant features without taking into account all possible transformations, which is demanding and may propagate noise due to pixel interpolations.…”

Section: Discussionmentioning

confidence: 99%

“…In [21], a transformation invariant RBM is proposed, where images are subjected to a predefined set of transformations. In [13] an RBM that learns equivariant features is proposed, whereby adding a new variable to be inferred within the hidden units, this variable is then used to rotate learned weights accordingly. In [19], a rotation (invariant) Convolutional RBM is proposed.…”

Section: Introductionmentioning

confidence: 99%

“…Then, patches are extracted on SIFT keypoints [18] and subsequently rotated and scaled accordingly. Despite their progress, the aforementioned methods share the following drawbacks: either they are limited to the set of transformations considered within the model, or they involve deep networks in the hope of learning better transformation invariant features [13,20,21], albeit increasing computational demand.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Rotation-Invariant Restricted Boltzmann Machine Using Shared Gradient Filters

Giuffrida

Tsaftaris

2016

Artificial Neural Networks and Machine Learning – ICANN 2016

View full text Add to dashboard Cite

Abstract. Finding suitable features has been an essential problem in computer vision. We focus on Restricted Boltzmann Machines (RBMs), which, despite their versatility, cannot accommodate transformations that may occur in the scene. As a result, several approaches have been proposed that consider a set of transformations, which are used to either augment the training set or transform the actual learned filters. In this paper, we propose the Explicit Rotation-Invariant Restricted Boltzmann Machine, which exploits prior information coming from the dominant orientation of images. Our model extends the standard RBM, by adding a suitable number of weight matrices, associated with each dominant gradient. We show that our approach is able to learn rotationinvariant features, comparing it with the classic formulation of RBM on the MNIST benchmark dataset. Overall, requiring less hidden units, our method learns compact features, which are robust to rotations.

show abstract

Graph Spectral Point Cloud Processing

Chen

Tian

2021

Graph Spectral Image Processing

View full text Add to dashboard Cite

Transformation Equivariant Boltzmann Machines

Cited by 46 publications

References 14 publications

Detection of Informal Settlements from VHR Images Using Convolutional Neural Networks

Detection of Informal Settlements from VHR Images Using Convolutional Neural Networks

Rotation-Invariant Restricted Boltzmann Machine Using Shared Gradient Filters

Graph Spectral Point Cloud Processing

Contact Info

Product

Resources

About