scholarly journals Label consistent transform learning for pattern classification

2019 ◽  
Vol 13 ◽  
pp. 174830261988139
Author(s):  
He-Feng Yin ◽  
Xiao-Jun Wu
Keyword(s):  
Image Processing ◽  
Pattern Classification ◽  
Dictionary Learning ◽  
Optimization Problem ◽  
Classification Performance ◽  
Alternative Strategy ◽  
Learning Approaches ◽  
Training Time ◽  
Practical Applications ◽  
Consistency Constraint

Transform learning has been successfully applied to various image processing tasks in recent years. Nevertheless, transform learning learns the representation in an unsupervised fashion. To make transform learning suitable for pattern classification, we introduce a label consistency constraint into transform learning and propose a new label consistent transform learning to enhance the classification performance of transform learning. The resulting optimization problem can be solved elegantly by employing the alternative strategy. Experimental results on publicly available databases demonstrate that label consistent transform learning outperforms several dictionary learning approaches and the recently proposed discriminative transform learning. More importantly, label consistent transform learning has the least training time which has the potential in practical applications.

scholarly journals Nonnegative Signal Decomposition with Supervision

2013 ◽  
Vol 2013 ◽  
pp. 1-8
Author(s):  
Teng Li ◽  
Huan Chang ◽  
Jun Wu
Keyword(s):  
Objective Function ◽  
Image Classification ◽  
Pattern Classification ◽  
Optimization Problem ◽  
Real Data ◽  
Classification Performance ◽  
Signal Decomposition ◽  
Weak Supervision ◽  
Training Samples ◽  
Novel Algorithm

This paper presents a novel algorithm to numerically decompose mixed signals in a collaborative way, given supervision of the labels that each signal contains. The decomposition is formulated as an optimization problem incorporating nonnegative constraint. A nonnegative data factorization solution is presented to yield the decomposed results. It is shown that the optimization is efficient and decreases the objective function monotonically. Such a decomposition algorithm can be applied on multilabel training samples for pattern classification. The real-data experimental results show that the proposed algorithm can significantly facilitate the multilabel image classification performance with weak supervision.

scholarly journals Shift Invariant Dictionary Learning for Human Action Recognition

2019 ◽  
Vol 9 (2) ◽  
pp. 2107-2111
Keyword(s):  
Sparse Representation ◽  
Action Recognition ◽  
Dictionary Learning ◽  
Human Action Recognition ◽  
Human Action ◽  
Signal Denoising ◽  
Learning Approaches ◽  
Training Time ◽  
Initial Stage ◽  
Shift Invariance

Sparse representation is an emerging topic among researchers. The method to represent the huge volume of dense data as sparse data is much needed for various fields such as classification, compression and signal denoising. The base of the sparse representation is dictionary learning. In most of the dictionary learning approaches, the dictionary is learnt based on the input training signals which consumes more time. To solve this issue, the shift-invariant dictionary is used for action recognition in this work. Shift-Invariant Dictionary (SID) is that the dictionary is constructed in the initial stage with shift-invariance of initial atoms. The advantage of the proposed SID based action recognition method is that it requires minimum training time and achieves highest accuracy.

scholarly journals Discriminative non-negative representation based classifier for image recognition

2021 ◽  
Vol 15 ◽  
pp. 174830262110449
Author(s):  
Kai-Jun Hu ◽  
He-Feng Yin ◽  
Jun Sun
Keyword(s):  
Pattern Classification ◽  
State Of The Art ◽  
Source Code ◽  
Classification Performance ◽  
Training Data ◽  
Practical Applications ◽  
The Past ◽  
Benchmark Datasets ◽  
Classification Tasks ◽  
Negative Representation

During the past decade, representation based classification method has received considerable attention in the community of pattern recognition. The recently proposed non-negative representation based classifier achieved superb recognition results in diverse pattern classification tasks. Unfortunately, discriminative information of training data is not fully exploited in non-negative representation based classifier, which undermines its classification performance in practical applications. To address this problem, we introduce a decorrelation regularizer into the formulation of non-negative representation based classifier and propose a discriminative non-negative representation based classifier for pattern classification. The decorrelation regularizer is able to reduce the correlation of representation results of different classes, thus promoting the competition among them. Experimental results on benchmark datasets validate the efficacy of the proposed discriminative non-negative representation based classifier, and it can outperform some state-of-the-art deep learning based methods. The source code of our proposed discriminative non-negative representation based classifier is accessible at https://github.com/yinhefeng/DNRC .

scholarly journals Contrastive Losses and Solution Caching for Predict-and-Optimize

2021 ◽  
Author(s):  
Maxime Mulamba ◽  
Jayanta Mandi ◽  
Michelangelo Diligenti ◽  
Michele Lombardi ◽  
Victor Bucarey ◽  
...  
Keyword(s):  
Optimization Problem ◽  
Computational Cost ◽  
Learning Approaches ◽  
Optimal Solutions ◽  
Training Time ◽  
Slow Growth Rate ◽  
Historic Data ◽  
Uncertain Input ◽  
Feasible Space ◽  
Inner Approximation

Many decision-making processes involve solving a combinatorial optimization problem with uncertain input that can be estimated from historic data. Recently, problems in this class have been successfully addressed via end-to-end learning approaches, which rely on solving one optimization problem for each training instance at every epoch. In this context, we provide two distinct contributions. First, we use a Noise Contrastive approach to motivate a family of surrogate loss functions, based on viewing non-optimal solutions as negative examples. Second, we address a major bottleneck of all predict-and-optimize approaches, i.e. the need to frequently recompute optimal solutions at training time. This is done via a solver-agnostic solution caching scheme, and by replacing optimization calls with a lookup in the solution cache. The method is formally based on an inner approximation of the feasible space and, combined with a cache lookup strategy, provides a controllable trade-off between training time and accuracy of the loss approximation. We empirically show that even a very slow growth rate is enough to match the quality of state-of-the-art methods, at a fraction of the computational cost.

scholarly journals Preparatory Experiments Regarding Human Brain Perception and Reasoning of Image Complexity for Synthetic Color Fractal and Natural Texture Images via EEG

2020 ◽  
Vol 11 (1) ◽  
pp. 164
Author(s):  
Irina E. Nicolae ◽  
Mihai Ivanovici
Keyword(s):  
Human Perception ◽  
Event Related Potentials ◽  
Classification Performance ◽  
Subjective Perception ◽  
Image Perception ◽  
Image Complexity ◽  
Temporal Area ◽  
Practical Applications ◽  
Related Potentials ◽  
Texture Complexity

Texture plays an important role in computer vision in expressing the characteristics of a surface. Texture complexity evaluation is important for relying not only on the mathematical properties of the digital image, but also on human perception. Human subjective perception verbally expressed is relative in time, since it can be influenced by a variety of internal or external factors, such as: Mood, tiredness, stress, noise surroundings, and so on, while closely capturing the thought processes would be more straightforward to human reasoning and perception. With the long-term goal of designing more reliable measures of perception which relate to the internal human neural processes taking place when an image is perceived, we firstly performed an electroencephalography experiment with eight healthy participants during color textural perception of natural and fractal images followed by reasoning on their complexity degree, against single color reference images. Aiming at more practical applications for easy use, we tested this entire setting with a WiFi 6 channels electroencephalography (EEG) system. The EEG responses are investigated in the temporal, spectral and spatial domains in order to assess human texture complexity perception, in comparison with both textural types. As an objective reference, the properties of the color textural images are expressed by two common image complexity metrics: Color entropy and color fractal dimension. We observed in the temporal domain, higher Event Related Potentials (ERPs) for fractal image perception, followed by the natural and one color images perception. We report good discriminations between perceptions in the parietal area over time and differences in the temporal area regarding the frequency domain, having good classification performance.

scholarly journals Analysis of the Nosema Cells Identification for Microscopic Images

Sensors ◽  
2021 ◽  
Vol 21 (9) ◽  
pp. 3068
Author(s):  
Soumaya Dghim ◽  
Carlos M. Travieso-González ◽  
Radim Burget
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Image Processing ◽  
Deep Learning ◽  
The Other ◽  
Support Vector ◽  
Learning Approaches ◽  
Microscopic Images ◽  
Trained Neural Network ◽  
Nosema Disease

The use of image processing tools, machine learning, and deep learning approaches has become very useful and robust in recent years. This paper introduces the detection of the Nosema disease, which is considered to be one of the most economically significant diseases today. This work shows a solution for recognizing and identifying Nosema cells between the other existing objects in the microscopic image. Two main strategies are examined. The first strategy uses image processing tools to extract the most valuable information and features from the dataset of microscopic images. Then, machine learning methods are applied, such as a neural network (ANN) and support vector machine (SVM) for detecting and classifying the Nosema disease cells. The second strategy explores deep learning and transfers learning. Several approaches were examined, including a convolutional neural network (CNN) classifier and several methods of transfer learning (AlexNet, VGG-16 and VGG-19), which were fine-tuned and applied to the object sub-images in order to identify the Nosema images from the other object images. The best accuracy was reached by the VGG-16 pre-trained neural network with 96.25%.

Practical Tools for Reasoning About Linear Constraints

1991 ◽  
Vol 15 (3-4) ◽  
pp. 357-379
Author(s):  
Tien Huynh ◽  
Leo Joskowicz ◽  
Catherine Lassez ◽  
Jean-Louis Lassez
Keyword(s):  
Logic Programming ◽  
Intelligent Systems ◽  
Optimization Problem ◽  
Spatial Reasoning ◽  
Quantifier Elimination ◽  
Canonical Representation ◽  
Linear Constraints ◽  
Practical Applications ◽  
Variable Elimination ◽  
Fourier Algorithm

We address the problem of building intelligent systems to reason about linear arithmetic constraints. We develop, along the lines of Logic Programming, a unifying framework based on the concept of Parametric Queries and a quasi-dual generalization of the classical Linear Programming optimization problem. Variable (quantifier) elimination is the key underlying operation which provides an oracle to answer all queries and plays a role similar to Resolution in Logic Programming. We discuss three methods for variable elimination, compare their feasibility, and establish their applicability. We then address practical issues of solvability and canonical representation, as well as dynamical updates and feedback. In particular, we show how the quasi-dual formulation can be used to achieve the discriminating characteristics of the classical Fourier algorithm regarding solvability, detection of implicit equalities and, in case of unsolvability, the detection of minimal unsolvable subsets. We illustrate the relevance of our approach with examples from the domain of spatial reasoning and demonstrate its viability with empirical results from two practical applications: computation of canonical forms and convex hull construction.

scholarly journals Train Fast While Reducing False Positives: Improving Animal Classification Performance Using Convolutional Neural Networks

Geomatics ◽  
2021 ◽  
Vol 1 (1) ◽  
pp. 34-49
Author(s):  
Mael Moreni ◽  
Jerome Theau ◽  
Samuel Foucher
Keyword(s):  
False Positive ◽  
Classification Performance ◽  
Large Datasets ◽  
False Positives ◽  
Fine Tuning ◽  
Training Time ◽  
In The Wild ◽  
Test Sets ◽  
High Level ◽  
Time Decrease

The combination of unmanned aerial vehicles (UAV) with deep learning models has the capacity to replace manned aircrafts for wildlife surveys. However, the scarcity of animals in the wild often leads to highly unbalanced, large datasets for which even a good detection method can return a large amount of false detections. Our objectives in this paper were to design a training method that would reduce training time, decrease the number of false positives and alleviate the fine-tuning effort of an image classifier in a context of animal surveys. We acquired two highly unbalanced datasets of deer images with a UAV and trained a Resnet-18 classifier using hard-negative mining and a series of recent techniques. Our method achieved sub-decimal false positive rates on two test sets (1 false positive per 19,162 and 213,312 negatives respectively), while training on small but relevant fractions of the data. The resulting training times were therefore significantly shorter than they would have been using the whole datasets. This high level of efficiency was achieved with little tuning effort and using simple techniques. We believe this parsimonious approach to dealing with highly unbalanced, large datasets could be particularly useful to projects with either limited resources or extremely large datasets.

Class-Aware Analysis Dictionary Learning for Pattern Classification

2017 ◽  
Vol 24 (12) ◽  
pp. 1822-1826 ◽  
Author(s):  
Jiujun Wang ◽  
Yanqing Guo ◽  
Jun Guo ◽  
Xiangyang Luo ◽  
Xiangwei Kong
Keyword(s):  
Pattern Classification ◽  
Dictionary Learning
Sign in / Sign up

Export Citation Format

Share Document