Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

The feed-forward architectures of recently proposed deep super-resolution networks learn representations of low-resolution inputs, and the non-linear mapping from those to high-resolution output. However, this approach does not fully address the mutual dependencies of low- and high-resolution images. We propose Deep Back-Projection Networks (DBPN), that exploit iterative up- and downsampling layers, providing an error feedback mechanism for projection errors at each stage. We construct mutually-connected up- and down-sampling stages each of which represents different types of image degradation and high-resolution components. We show that extending this idea to allow concatenation of features across up- and downsampling stages (Dense DBPN) allows us to reconstruct further improve super-resolution, yielding superior results and in particular establishing new state of the art results for large scaling factors such as 8A— across multiple data sets.

/pdf/deep-back-projection-networks-for-super-resolution-49o16oqz1j.pdf

Deep Back-Projection Networks for Super-Resolution

In this paper, we propose a spectral–spatial feature based classification (SSFC) framework that jointly uses dimension reduction and deep learning techniques for spectral and spatial feature extraction, respectively. In this framework, a balanced local discriminant embedding algorithm is proposed for spectral feature extraction from high-dimensional hyperspectral data sets. In the meantime, convolutional neural network is utilized to automatically find spatial-related features at high levels. Then, the fusion feature is extracted by stacking spectral and spatial features together. Finally, the multiple-feature-based classifier is trained for image classification. Experimental results on well-known hyperspectral data sets show that the proposed SSFC method outperforms other commonly used methods for hyperspectral image classification.

Spectral–Spatial Feature Extraction for Hyperspectral Image Classification: A Dimension Reduction and Deep Learning Approach

We develop a novel maximum neighborhood margin discriminant projection (MNMDP) technique for dimensionality reduction of high-dimensional data. It utilizes both the local information and class information to model the intraclass and interclass neighborhood scatters. By maximizing the margin between intraclass and interclass neighborhoods of all points, MNMDP cannot only detect the true intrinsic manifold structure of the data but also strengthen the pattern discrimination among different classes. To verify the classification performance of the proposed MNMDP, it is applied to the PolyU HRF and FKP databases, the AR face database, and the UCI Musk database, in comparison with the competing methods such as PCA and LDA. The experimental results demonstrate the effectiveness of our MNMDP in pattern classification.

/pdf/maximum-neighborhood-margin-discriminant-projection-for-4vo54g9wbt.pdf

Maximum neighborhood margin discriminant projection for classification

In palmprint recognition field, orientation based approaches are thought to achieve the best results in terms of recognition rates. In this paper, we propose a novel orientation based scheme, in which three strategies, the modified finite Radon transform, enlarged training set and pixel to area matching, have been designed to further improve its performance. The experimental results of verification conducted on Hong Kong Polytechnic University Palmprint Database show that our approach has higher recognition rates and faster processing speed.

Palmprint Verification Based on Robust Orientation Code

Palmprint verification based on principal lines

http://www.nlpr.ia.ac.cn/2012papers/gjkw/gk63.pdf

Discriminant sparse neighborhood preserving embedding for face recognition

In this brief, a novel local descriptor, named local binary count (LBC), is proposed for rotation invariant texture classification. The proposed LBC can extract the local binary grayscale difference information, and totally abandon the local binary structural information. Although the LBC codes do not represent visual microstructure, the statistics of LBC features can represent the local texture effectively. In addition, a completed LBC (CLBC) is also proposed to enhance the performance of texture classification. Experimental results obtained from three databases demonstrate that the proposed CLBC can achieve comparable accurate classification rates with completed local binary pattern.

Completed Local Binary Count for Rotation Invariant Texture Classification

In this brief, we propose a novel contour-based shape descriptor, called the multiscale distance matrix, to capture the shape geometry while being invariant to translation, rotation, scaling, and bilateral symmetry. The descriptor is further combined with a dimensionality reduction to improve its discriminative power. The proposed method avoids the time-consuming pointwise matching encountered in most of the previously used shape recognition algorithms. It is therefore fast and suitable for real-time applications. We applied the proposed method to the task of plan leaf recognition with experiments on two data sets, the Swedish Leaf data set and the ICL Leaf data set. The experimental results clearly demonstrate the effectiveness and efficiency of the proposed descriptor.

Wei Jia

Papers

Palmprint Verification Based on Robust Orientation Code

Palmprint verification based on principal lines

Discriminant sparse neighborhood preserving embedding for face recognition

Completed Local Binary Count for Rotation Invariant Texture Classification

Multiscale Distance Matrix for Fast Plant Leaf Recognition