scholarly journals Discriminative Center Loss for Face Photo-Sketch Recognition

2020 ◽  
Author(s):  
lin cao ◽  
xibao huo ◽  
yanan guo ◽  
yuying shao ◽  
kangning du
Keyword(s):  
Small Sample ◽  
Discriminative Power ◽  
Sample Problem ◽  
Sketch Recognition ◽  
Regularization Technique ◽  
Large Domain ◽  
Class Separability ◽  
Center Loss ◽  
Small Sample Problem ◽  
Learned Features

Abstract Face photo-sketch recognition refers to the process of matching sketches to photos. Recently, there has been a growing interest in using a convolutional neural network to learn discriminatively deep features. However, due to the large domain discrepancy and the high cost of acquiring sketches, the discriminative power of the deeply learned features will be inevitably reduced. In this paper, we propose a discriminative center loss to learn domain invariant features for face photo-sketch recognition. Specifically, two Mahalanobis distance matrices are proposed to enhance the intra-class compactness during inter-class separability. Moreover, a regularization technique is adopted on the Mahalanobis matrices to alleviate the small sample problem. Extensive experimental results on the e-PRIP dataset verified the effectiveness of the proposed discriminative center loss.

scholarly journals Semantic Locality-Aware Deformable Network for Clothing Segmentation

2018 ◽  
Author(s):  
Wei Ji ◽  
Xi Li ◽  
Yueting Zhuang ◽  
Omar El Farouk Bourahla ◽  
Yixin Ji ◽  
...  
Keyword(s):  
Learning Process ◽  
State Of The Art ◽  
Semantic Segmentation ◽  
Small Sample ◽  
Sample Problem ◽  
Fine Grained ◽  
Domain Specific ◽  
Proposed Model ◽  
Segmentation Framework ◽  
Small Sample Problem

Clothing segmentation is a challenging vision problem typically implemented within a fine-grained semantic segmentation framework. Different from conventional segmentation, clothing segmentation has some domain-specific properties such as texture richness, diverse appearance variations, non-rigid geometry deformations, and small sample learning. To deal with these points, we propose a semantic locality-aware segmentation model, which adaptively attaches an original clothing image with a semantically similar (e.g., appearance or pose) auxiliary exemplar by search. Through considering the interactions of the clothing image and its exemplar, more intrinsic knowledge about the locality manifold structures of clothing images is discovered to make the learning process of small sample problem more stable and tractable. Furthermore, we present a CNN model based on the deformable convolutions to extract the non-rigid geometry-aware features for clothing images. Experimental results demonstrate the effectiveness of the proposed model against the state-of-the-art approaches.

scholarly journals Multiscale Information Fusion for Hyperspectral Image Classification Based on Hybrid 2D-3D CNN

2021 ◽  
Vol 13 (12) ◽  
pp. 2268
Author(s):  
Hang Gong ◽  
Qiuxia Li ◽  
Chunlai Li ◽  
Haishan Dai ◽  
Zhiping He ◽  
...  
Keyword(s):  
Classification Accuracy ◽  
Spatial Information ◽  
Hyperspectral Image ◽  
Small Sample ◽  
Hyperspectral Images ◽  
Sample Problem ◽  
Training Samples ◽  
Small Sample Problem ◽  
3D Cnn ◽  
Hyperspectral Classification

Hyperspectral images are widely used for classification due to its rich spectral information along with spatial information. To process the high dimensionality and high nonlinearity of hyperspectral images, deep learning methods based on convolutional neural network (CNN) are widely used in hyperspectral classification applications. However, most CNN structures are stacked vertically in addition to using a onefold size of convolutional kernels or pooling layers, which cannot fully mine the multiscale information on the hyperspectral images. When such networks meet the practical challenge of a limited labeled hyperspectral image dataset—i.e., “small sample problem”—the classification accuracy and generalization ability would be limited. In this paper, to tackle the small sample problem, we apply the semantic segmentation function to the pixel-level hyperspectral classification due to their comparability. A lightweight, multiscale squeeze-and-excitation pyramid pooling network (MSPN) is proposed. It consists of a multiscale 3D CNN module, a squeezing and excitation module, and a pyramid pooling module with 2D CNN. Such a hybrid 2D-3D-CNN MSPN framework can learn and fuse deeper hierarchical spatial–spectral features with fewer training samples. The proposed MSPN was tested on three publicly available hyperspectral classification datasets: Indian Pine, Salinas, and Pavia University. Using 5%, 0.5%, and 0.5% training samples of the three datasets, the classification accuracies of the MSPN were 96.09%, 97%, and 96.56%, respectively. In addition, we also selected the latest dataset with higher spatial resolution, named WHU-Hi-LongKou, as the challenge object. Using only 0.1% of the training samples, we could achieve a 97.31% classification accuracy, which is far superior to the state-of-the-art hyperspectral classification methods.

scholarly journals WMW-A: Rank-based two-sample independent test for small sample sizes through an auxiliary sample

2021 ◽  
Author(s):  
Yin Guo ◽  
Limin Li
Keyword(s):  
Gene Expression ◽  
Case Control ◽  
Test Methods ◽  
Small Sample ◽  
Sample Problem ◽  
Auxiliary Data ◽  
Independent Test ◽  
Small Sample Problem ◽  
Small Sample Sizes ◽  
And Control

Two-sample independent test methods are widely used in case-control studies to identify significant changes or differences, for example, to identify key pathogenic genes by comparing the gene expression levels in normal and disease cells. However, due to the high cost of data collection or labelling, many studies face the small sample problem, for which the traditional two-sample test methods often lose power. We propose a novel rank-based nonparametric test method WMW-A for small sample problem by introducing a three-sample statistic through another auxiliary sample. By combining the case, control and auxiliary samples together, we construct a three-sample WMW-A statistic based on the gap between the average ranks of the case and control samples in the combined samples. By assuming that the auxiliary sample follows a mixed distribution of the case and control populations, we analyze the theoretical properties of the WMW-A statistic and approximate the theoretical power. The extensive simulation experiments and real applications on microarray gene expression data sets show the WMW-A test could significantly improve the test power for two-sample problem with small sample sizes, by either available unlabelled auxiliary data or generated auxiliary data.

scholarly journals Sticky cost behavior of bank’s executive compensation in four South East Asian countries

2017 ◽  
Vol 19 (3) ◽  
Author(s):  
Etik Kresnawati ◽  
Slamet Sugiri ◽  
Rahmat Febrianto
Keyword(s):  
Executive Compensation ◽  
Bootstrap Method ◽  
East Asian ◽  
Small Sample ◽  
Manufacturing Companies ◽  
Asian Countries ◽  
Sample Problem ◽  
Cost Behavior ◽  
Small Sample Problem ◽  
New Perspective

Some studies indicate that selling, general, and administrative (SG&A) cost have sticky characteristics. A cost is sticky if it increases as the activity increases, but it does not decrease as the activity decreases, in the same proportion as it increases. Different from previous studies that focus solely on SG&A costs in, mostly, manufacturing companies, we specifically focus on specific cost and specific industry. In this case, we focus on compensation costs in banks from four South East Asian countries. We choose banks’ executive compensations since banks in South East Asia have been publicly reporting their compensation. Executive compensation itself is a component of SG&A, so it may have sticky characteristic with it. We apply bootstrap method to tackle small sample problem in every country. Results show that executive compensations are not sticky, but, on the contrary, anti-sticky since the compensation decreases faster when the revenue decreases than its increases when the revenue increases. This finding gives a new perspective on the characteristics of executive compensation expenses as a part of SG&A cost.

INFORMATION DIFFUSION TECHNIQUES AND SMALL-SAMPLE PROBLEM

2002 ◽  
Vol 01 (02) ◽  
pp. 229-249 ◽  
Author(s):  
CHONGFU HUANG
Keyword(s):  
Pattern Recognition ◽  
Information Diffusion ◽  
Information Matrix ◽  
Small Sample ◽  
The Self ◽  
Sample Problem ◽  
Compression Technique ◽  
Self Study ◽  
Digital Image Compression ◽  
Small Sample Problem

Strong interests in the small-sample problem have been given towards for establishing several information diffusion techniques for pattern recognition. In this paper, we review and formalize three techniques: the soft histogram, the self-study discrete regression, and the interior-outer-set model. To promote the development of this area, in this paper we suggest two open topics: the anti-accuracy principle and the digital image compression technique based on the fuzzy if-then rules extracted by using information matrix technique.

Sign in / Sign up

Export Citation Format

Share Document