Journal ArticleDOI
Feature Extraction With Deep Neural Networks by a Generalized Discriminant Analysis
Reads0
Chats0
TLDR
The generalized discriminant analysis (GerDA) proposed in this paper uses nonlinear transformations that are learnt by DNNs in a semisupervised fashion and displays excellent performance on real-world recognition and detection tasks, such as handwritten digit recognition and face detection.Abstract:
We present an approach to feature extraction that is a generalization of the classical linear discriminant analysis (LDA) on the basis of deep neural networks (DNNs). As for LDA, discriminative features generated from independent Gaussian class conditionals are assumed. This modeling has the advantages that the intrinsic dimensionality of the feature space is bounded by the number of classes and that the optimal discriminant function is linear. Unfortunately, linear transformations are insufficient to extract optimal discriminative features from arbitrarily distributed raw measurements. The generalized discriminant analysis (GerDA) proposed in this paper uses nonlinear transformations that are learnt by DNNs in a semisupervised fashion. We show that the feature extraction based on our approach displays excellent performance on real-world recognition and detection tasks, such as handwritten digit recognition and face detection. In a series of experiments, we evaluate GerDA features with respect to dimensionality reduction, visualization, classification, and detection. Moreover, we show that GerDA DNNs can preprocess truly high-dimensional input data to low-dimensional representations that facilitate accurate predictions even if simple linear predictors or measures of similarity are used.read more
Citations
More filters
Journal ArticleDOI
Object Detection With Deep Learning: A Review
TL;DR: In this article, a review of deep learning-based object detection frameworks is provided, focusing on typical generic object detection architectures along with some modifications and useful tricks to improve detection performance further.
Journal ArticleDOI
Change Detection in Synthetic Aperture Radar Images Based on Deep Neural Networks
TL;DR: This paper presents a novel change detection approach for synthetic aperture radar images based on deep learning that accomplishes the detection of the changed and unchanged areas by designing a deep neural network.
Journal ArticleDOI
Salient Band Selection for Hyperspectral Image Classification via Manifold Ranking
Qi Wang,Jianzhe Lin,Yuan Yuan +2 more
TL;DR: This paper proposes to eliminate the drawbacks of traditional salient band selection methods by manifold ranking and puts the band vectors in the more accurate manifold space and treats the saliency problem from a novel ranking perspective, which is considered to be the main contributions of this paper.
Journal ArticleDOI
Deep Neural Network for Structural Prediction and Lane Detection in Traffic Scene
TL;DR: A multitask deep convolutional network is developed, which simultaneously detects the presence of the target and the geometric attributes of thetarget with respect to the region of interest and a recurrent neuron layer is adopted for structured visual detection.
Journal ArticleDOI
On Deep Learning for Trust-Aware Recommendations in Social Networks
TL;DR: A two-phase recommendation process is proposed to utilize deep learning to determinate the initialization in MF for trust-aware social recommendations and to differentiate the community effect in user’s trusted friendships.
References
More filters
Journal ArticleDOI
Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images
Stuart Geman,Donald Geman +1 more
TL;DR: The analogy between images and statistical mechanics systems is made and the analogous operation under the posterior distribution yields the maximum a posteriori (MAP) estimate of the image given the degraded observations, creating a highly parallel ``relaxation'' algorithm for MAP estimation.
Journal ArticleDOI
Reducing the Dimensionality of Data with Neural Networks
TL;DR: In this article, an effective way of initializing the weights that allows deep autoencoder networks to learn low-dimensional codes that work much better than principal components analysis as a tool to reduce the dimensionality of data is described.
Journal ArticleDOI
A fast learning algorithm for deep belief nets
TL;DR: A fast, greedy algorithm is derived that can learn deep, directed belief networks one layer at a time, provided the top two layers form an undirected associative memory.
Book
Image Processing: Analysis and Machine Vision
TL;DR: The digitized image and its properties are studied, including shape representation and description, and linear discrete image transforms, and texture analysis.