scholarly journals Cross-Modality Person Re-Identification Based on Heterogeneous Center Loss and Non-Local Features

Entropy ◽  
2021 ◽  
Vol 23 (7) ◽  
pp. 919
Author(s):  
Chengmei Han ◽  
Peng Pan ◽  
Aihua Zheng ◽  
Jin Tang
Keyword(s):  
Feature Learning ◽  
Feature Representation ◽  
Low Light ◽  
Local Mechanism ◽  
Neural Network Structure ◽  
Non Local ◽  
Center Loss ◽  
Infrared Cameras ◽  
The One ◽  
Feature Expression

Cross-modality person re-identification is the study of images of people matching under different modalities (RGB modality, IR modality). Given one RGB image of a pedestrian collected under visible light in the daytime, cross-modality person re-identification aims to determine whether the same pedestrian appears in infrared images (IR images) collected by infrared cameras at night, and vice versa. Cross-modality person re-identification can solve the task of pedestrian recognition in low light or at night. This paper aims to improve the degree of similarity for the same pedestrian in two modalities by improving the feature expression ability of the network and designing appropriate loss functions. To implement our approach, we introduce a deep neural network structure combining heterogeneous center loss (HC loss) and a non-local mechanism. On the one hand, this can heighten the performance of feature representation of the feature learning module, and, on the other hand, it can improve the similarity of cross-modality within the class. Experimental data show that the network achieves excellent performance on SYSU-MM01 datasets.

scholarly journals Neural network feature learning based on image self-encoding

2020 ◽  
Vol 17 (2) ◽  
pp. 172988142092165
Author(s):  
Yangyang Liu ◽  
Minghua Tian ◽  
Chang Xu ◽  
Lixiang Zhao
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Image Retrieval ◽  
Image Coding ◽  
Rapid Development ◽  
Feature Learning ◽  
Feature Representation ◽  
The Neural Network ◽  
Network Feature ◽  
Feature Expression

With the rapid development of information technology and the arrival of the era of big data, people’s access to information is increasingly relying on information such as images. Today, image data are showing an increasing trend in the form of an index. How to use deep learning models to extract valuable information from massive data is very important. In the face of such a situation, people cannot accurately and timely find out the information they need. Therefore, the research on image retrieval technology is very important. Image retrieval is an important technology in the field of computer vision image processing. It realizes fast and accurate query of similar images in image database. The excellent feature representation not only can represent the category information of the image but also capture the relevant semantic information of the image. If the neural network feature learning expression is combined with the image retrieval field, it will definitely improve the application of image retrieval technology. To solve the above problems, this article studies the problems encountered in deep learning neural network feature learning based on image self-encoding and discusses its feature expression in the field of image retrieval. By adding the spatial relationship information obtained by image self-encoding in the neural network training process, the feature expression ability of the selected neural network is improved, and the neural network feature learning based on image coding is successfully applied to the popular field of image retrieval.

Changes in the Stoichiometry of Photosystem II Components as an Adaptive Response to High-Light and Low-Light Conditions during Growth

1986 ◽  
Vol 41 (5-6) ◽  
pp. 597-603 ◽  
Author(s):  
Aloysius Wild ◽  
Matthias Höpfner ◽  
Wolfgang Rühle ◽  
Michael Richter
Keyword(s):  
Photosystem Ii ◽  
Functional Organization ◽  
Photosynthetic Apparatus ◽  
High Light ◽  
Molar Ratio ◽  
Light Conditions ◽  
Low Light ◽  
Pigment System ◽  
Transport Chain ◽  
The One

The effect of different growth light intensities (60 W·m-2, 6 W·m-2) on the performance of the photosynthetic apparatus of mustard plants (Sinapis alba L.) was studied. A distinct decrease in photosystem II content per chlorophyll under low-light conditions compared to high-light conditions was found. For P-680 as well as for Oᴀ and Oв protein the molar ratio between high-light and low-light plants was 1.4 whereas the respective concentrations per chlorophyll showed some variations for P-680 and Oᴀ on the one and Oв protein on the other hand.In addition to the study of photosystem II components, the concentrations of PQ, Cyt f, and P-700 were measured. The light regime during growth had no effect on the amount of P-700 per chlorophyll but there were large differences with respect to PQ and Cyt f. The molar ratio for Cyt f and PQ between high- and low-light leaves was 2.2 and 1.9, respectively.Two models are proposed, showing the functional organization of the pigment system and the electron transport chain in thylakoids of high-light and low-light leaves of mustard plants.

scholarly journals Disentangled Feature Learning Network for Vehicle Re-Identification

2020 ◽  
Author(s):  
Yan Bai ◽  
Yihang Lou ◽  
Yongxing Dai ◽  
Jun Liu ◽  
Ziqian Chen ◽  
...  
Keyword(s):  
State Of The Art ◽  
Feature Learning ◽  
Feature Representation ◽  
Public Security ◽  
The Public ◽  
Common Features ◽  
Learning Network ◽  
Single Feature ◽  
Art Performance

Vehicle Re-Identification (ReID) has attracted lots of research efforts due to its great significance to the public security. In vehicle ReID, we aim to learn features that are powerful in discriminating subtle differences between vehicles which are visually similar, and also robust against different orientations of the same vehicle. However, these two characteristics are hard to be encapsulated into a single feature representation simultaneously with unified supervision. Here we propose a Disentangled Feature Learning Network (DFLNet) to learn orientation specific and common features concurrently, which are discriminative at details and invariant to orientations, respectively. Moreover, to effectively use these two types of features for ReID, we further design a feature metric alignment scheme to ensure the consistency of the metric scales. The experiments show the effectiveness of our method that achieves state-of-the-art performance on three challenging datasets.

scholarly journals Wheel fault diagnosis model based on multichannel attention and supervised contrastive learning

2021 ◽  
Vol 13 (12) ◽  
pp. 168781402110670
Author(s):  
Yanxiang Chen ◽  
Zuxing Zhao ◽  
Euiyoul Kim ◽  
Haiyang Liu ◽  
Juan Xu ◽  
...  
Keyword(s):  
Network Architecture ◽  
Feature Learning ◽  
Feature Representation ◽  
Diagnostic Methods ◽  
Learning Ability ◽  
Noise Interference ◽  
Backbone Network ◽  
Mechanical Methods ◽  
Wheel Flat ◽  
Wheel Radius

As wheels are important components of train operation, diagnosing and predicting wheel faults are essential to ensure the reliability of rail transit. Currently, the existing studies always separately deal with two main types of wheel faults, namely wheel radius difference and wheel flat, even though they are both reflected by wheel radius changes. Moreover, traditional diagnostic methods, such as mechanical methods or a combination of data analysis methods, have limited abilities to efficiently extract data features. Deep learning models have become useful tools to automatically learn features from raw vibration signals. However, research on improving the feature-learning capabilities of models under noise interference to yield higher wheel diagnostic accuracies has not yet been conducted. In this paper, a unified training framework with the same model architecture and loss function is established for two homologous wheel faults. After selecting deep residual networks (ResNets) as the backbone network to build the model, we add the squeeze and excitation (SE) module based on a multichannel attention mechanism to the backbone network to learn the global relationships among feature channels. Then the influence of noise interference features is reduced while the extraction of useful information features is enhanced, leading to the improved feature-learning ability of ResNet. To further obtain effective feature representation using the model, we introduce supervised contrastive loss (SCL) on the basis of ResNet + SE to enlarge the feature distances of different fault classes through a comparison between positive and negative examples under label supervision to obtain a better class differentiation and higher diagnostic accuracy. We also complete a regression task to predict the fault degrees of wheel radius difference and wheel flat without changing the network architecture. The extensive experimental results show that the proposed model has a high accuracy in diagnosing and predicting two types of wheel faults.

scholarly journals Ontology of a Wavefunction from the Perspective of an Invariant Proper Time

2021 ◽  
Author(s):  
Salim Yasmineh
Keyword(s):  
Quantum Mechanics ◽  
Special Relativity ◽  
Proper Time ◽  
Finite Density ◽  
Confining Potential ◽  
Standard Time ◽  
Related Matter ◽  
Local Mechanism ◽  
Non Local ◽  
The Individual

All the arguments of a wavefunction are defined at the same instant implying a notion of simultaneity. In a somewhat related matter, certain phenomena in quantum mechanics seem to have non-local causal relations. Both concepts are in contradiction with special relativity. We propose to define the wavefunction with respect to the invariant proper time of special relativity instead of standard time. Moreover, we shall adopt the original idea of Schrodinger suggesting that the wavefunction represents an ontological cloud-like object that we shall call ‘individual fabric’ that has a finite density amplitude vanishing at infinity. Consequently, measurement can be assimilated to a confining potential that triggers an inherent non-local mechanism within the individual fabric. It is formalised by multiplying the wavefunction with a localising gaussian as in the GRW theory but in a deterministic manner.

scholarly journals Pyramid Constrained Self-Attention Network for Fast Video Salient Object Detection

2020 ◽  
Vol 34 (07) ◽  
pp. 10869-10876 ◽  
Author(s):  
Yuchao Gu ◽  
Lijuan Wang ◽  
Ziqin Wang ◽  
Yun Liu ◽  
Ming-Ming Cheng ◽  
...  
Keyword(s):  
Object Detection ◽  
Short Term Memory ◽  
Salient Object Detection ◽  
Object Motion ◽  
Salient Object ◽  
Motion Cues ◽  
Spatiotemporal Information ◽  
Local Mechanism ◽  
Non Local ◽  
Pyramid Structures

Spatiotemporal information is essential for video salient object detection (VSOD) due to the highly attractive object motion for human's attention. Previous VSOD methods usually use Long Short-Term Memory (LSTM) or 3D ConvNet (C3D), which can only encode motion information through step-by-step propagation in the temporal domain. Recently, the non-local mechanism is proposed to capture long-range dependencies directly. However, it is not straightforward to apply the non-local mechanism into VSOD, because i) it fails to capture motion cues and tends to learn motion-independent global contexts; ii) its computation and memory costs are prohibitive for video dense prediction tasks such as VSOD. To address the above problems, we design a Constrained Self-Attention (CSA) operation to capture motion cues, based on the prior that objects always move in a continuous trajectory. We group a set of CSA operations in Pyramid structures (PCSA) to capture objects at various scales and speeds. Extensive experimental results demonstrate that our method outperforms previous state-of-the-art methods in both accuracy and speed (110 FPS on a single Titan Xp) on five challenge datasets. Our code is available at https://github.com/guyuchao/PyramidCSA.

scholarly journals Visual Object Tracking in RGB-D Data via Genetic Feature Learning

Complexity ◽  
2019 ◽  
Vol 2019 ◽  
pp. 1-8
Author(s):  
Ming-xin Jiang ◽  
Xian-xian Luo ◽  
Tao Hai ◽  
Hai-yan Wang ◽  
Song Yang ◽  
...  
Keyword(s):  
Object Tracking ◽  
Feature Learning ◽  
Feature Representation ◽  
Visual Object ◽  
Visual Object Tracking ◽  
Fitness Evaluation ◽  
Candidate Solution ◽  
Genetic Feature ◽  
Computer Vision Applications ◽  
Crossover And Mutation

Visual object tracking is a fundamental component in many computer vision applications. Extracting robust features of object is one of the most important steps in tracking. As trackers, only formulated on RGB data, are usually affected by occlusions, appearance, or illumination variations, we propose a novel RGB-D tracking method based on genetic feature learning in this paper. Our approach addresses feature learning as an optimization problem. As owning the advantage of parallel computing, genetic algorithm (GA) has fast speed of convergence and excellent global optimization performance. At the same time, unlike handcrafted feature and deep learning methods, GA can be employed to solve the problem of feature representation without prior knowledge, and it has no use for a large number of parameters to be learned. The candidate solution in RGB or depth modality is represented as an encoding of an image in GA, and genetic feature is learned through population initialization, fitness evaluation, selection, crossover, and mutation. The proposed RGB-D tracker is evaluated on popular benchmark dataset, and experimental results indicate that our method achieves higher accuracy and faster tracking speed.

scholarly journals R2FA-Det: Delving into High-Quality Rotatable Boxes for Ship Detection in SAR Images

2020 ◽  
Vol 12 (12) ◽  
pp. 2031 ◽  
Author(s):  
Shiqi Chen ◽  
Jun Zhang ◽  
Ronghui Zhan
Keyword(s):  
High Speed ◽  
Detection Efficiency ◽  
Feature Representation ◽  
Sar Images ◽  
Shape Information ◽  
Ship Detection ◽  
Accurate Localization ◽  
Aspect Ratios ◽  
Non Local ◽  
Experimental Validations

Recently, convolutional neural network (CNN)-based methods have been extensively explored for ship detection in synthetic aperture radar (SAR) images due to their powerful feature representation abilities. However, there are still several obstacles hindering the development. First, ships appear in various scenarios, which makes it difficult to exclude the disruption of the cluttered background. Second, it becomes more complicated to precisely locate the targets with large aspect ratios, arbitrary orientations and dense distributions. Third, the trade-off between accurate localization and improved detection efficiency needs to be considered. To address these issues, this paper presents a rotate refined feature alignment detector (R 2 FA-Det), which ingeniously balances the quality of bounding box prediction and the high speed of the single-stage framework. Specifically, first, we devise a lightweight non-local attention module and embed it into the stem network. The recalibration of features not only strengthens the object-related features yet adequately suppresses the background interference. In addition, both forms of anchors are integrated into our modified anchor mechanism and thus can enable better representation of densely arranged targets with less computation burden. Furthermore, considering the shortcoming of the feature misalignment existing in the cascaded refinement scheme, a feature-guided alignment module which encodes both the position and shape information of current refined anchors into the feature points is adopted. Extensive experimental validations on two SAR ship datasets are performed and the results demonstrate that our algorithm has higher accuracy with faster speed than some state-of-the-art methods.

Sign in / Sign up

Export Citation Format

Share Document