Circle-Based Ratio Loss for Person Reidentification

Person reidentification (re-id) aims to recognize a specific pedestrian from uncrossed surveillance camera views. Most re-id methods perform the retrieval task by comparing the similarity of pedestrian features extracted from deep learning models. Therefore, learning a discriminative feature is critical for person reidentification. Many works supervise the model learning with one or more loss functions to obtain the discriminability of features. Softmax loss is one of the widely used loss functions in re-id. However, traditional softmax loss inherently focuses on the feature separability and fails to consider the compactness of within-class features. To further improve the accuracy of re-id, many efforts are conducted to shrink within-class discrepancy as well as between-class similarity. In this paper, we propose a circle-based ratio loss for person re-identification. Concretely, we normalize the learned features and classification weights to map these vectors in the hypersphere. Then we take the ratio of the maximal intraclass distance and the minimal interclass distance as an objective loss, so the between-class separability and within-class compactness can be optimized simultaneously during the training stage. Finally, with the joint training of an improved softmax loss and the ratio loss, the deep model could mine discriminative pedestrian information and learn robust features for the re-id task. Comprehensive experiments on three re-id benchmark datasets are carried out to illustrate the effectiveness of the proposed method. Specially, 83.12% mAP on Market-1501, 71.70% mAP on DukeMTMC-reID, and 66.26%/63.24% mAP on CUHK03 labeled/detected are achieved, respectively.

Download Full-text

A Lightweight Dense Connected Approach with Attention on Single Image Super-Resolution

Electronics ◽

10.3390/electronics10111234 ◽

2021 ◽

Vol 10 (11) ◽

pp. 1234

Author(s):

Lei Zha ◽

Yu Yang ◽

Zicheng Lai ◽

Ziwei Zhang ◽

Juan Wen

Keyword(s):

Receptive Fields ◽

Super Resolution ◽

Feature Representation ◽

Single Image ◽

Deep Model ◽

Benchmark Datasets ◽

Rich Information ◽

Image Super Resolution ◽

Model Training ◽

Single Image Super Resolution

In recent years, neural networks for single image super-resolution (SISR) have applied more profound and deeper network structures to extract extra image details, which brings difficulties in model training. To deal with deep model training problems, researchers utilize dense skip connections to promote the model’s feature representation ability by reusing deep features of different receptive fields. Benefiting from the dense connection block, SRDensenet has achieved excellent performance in SISR. Despite the fact that the dense connected structure can provide rich information, it will also introduce redundant and useless information. To tackle this problem, in this paper, we propose a Lightweight Dense Connected Approach with Attention for Single Image Super-Resolution (LDCASR), which employs the attention mechanism to extract useful information in channel dimension. Particularly, we propose the recursive dense group (RDG), consisting of Dense Attention Blocks (DABs), which can obtain more significant representations by extracting deep features with the aid of both dense connections and the attention module, making our whole network attach importance to learning more advanced feature information. Additionally, we introduce the group convolution in DABs, which can reduce the number of parameters to 0.6 M. Extensive experiments on benchmark datasets demonstrate the superiority of our proposed method over five chosen SISR methods.

Download Full-text

Unsupervised Deep Learning via Affinity Diffusion

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i07.6757 ◽

2020 ◽

Vol 34 (07) ◽

pp. 11029-11036

Author(s):

Jiabo Huang ◽

Qi Dong ◽

Shaogang Gong ◽

Xiatian Zhu

Keyword(s):

Deep Learning ◽

State Of The Art ◽

General Purpose ◽

Training Data ◽

Learning Approach ◽

Model Learning ◽

Feature Representations ◽

Discriminative Feature ◽

Training Samples ◽

Unsupervised Deep Learning

Convolutional neural networks (CNNs) have achieved unprecedented success in a variety of computer vision tasks. However, they usually rely on supervised model learning with the need for massive labelled training data, limiting dramatically their usability and deployability in real-world scenarios without any labelling budget. In this work, we introduce a general-purpose unsupervised deep learning approach to deriving discriminative feature representations. It is based on self-discovering semantically consistent groups of unlabelled training samples with the same class concepts through a progressive affinity diffusion process. Extensive experiments on object image classification and clustering show the performance superiority of the proposed method over the state-of-the-art unsupervised learning models using six common image recognition benchmarks including MNIST, SVHN, STL10, CIFAR10, CIFAR100 and ImageNet.

Download Full-text

Using discriminative vector machine model with 2DPCA to predict interactions among proteins

BMC Bioinformatics ◽

10.1186/s12859-019-3268-5 ◽

2019 ◽

Vol 20 (S25) ◽

Cited By ~ 1

Author(s):

Zhengwei Li ◽

Ru Nie ◽

Zhuhong You ◽

Chen Cao ◽

Jiashu Li

Keyword(s):

Protein Interactions ◽

False Positive Rate ◽

Principal Component ◽

Amino Acid Sequences ◽

Support Vector ◽

Machine Model ◽

Discriminative Feature ◽

Benchmark Datasets ◽

Low Efficiency ◽

H Pylori

Abstract Background The interactions among proteins act as crucial roles in most cellular processes. Despite enormous effort put for identifying protein-protein interactions (PPIs) from a large number of organisms, existing firsthand biological experimental methods are high cost, low efficiency, and high false-positive rate. The application of in silico methods opens new doors for predicting interactions among proteins, and has been attracted a great deal of attention in the last decades. Results Here we present a novelty computational model with the adoption of our proposed Discriminative Vector Machine (DVM) model and a 2-Dimensional Principal Component Analysis (2DPCA) descriptor to identify candidate PPIs only based on protein sequences. To be more specific, a 2DPCA descriptor is employed to capture discriminative feature information from Position-Specific Scoring Matrix (PSSM) of amino acid sequences by the tool of PSI-BLAST. Then, a robust and powerful DVM classifier is employed to infer PPIs. When applied on both gold benchmark datasets of Yeast and H. pylori, our model obtained mean prediction accuracies as high as of 97.06 and 92.89%, respectively, which demonstrates a noticeable improvement than some state-of-the-art methods. Moreover, we constructed Support Vector Machines (SVM) based predictive model and made comparison it with our model on Human benchmark dataset. In addition, to further demonstrate the predictive reliability of our proposed method, we also carried out extensive experiments for identifying cross-species PPIs on five other species datasets. Conclusions All the experimental results indicate that our method is very effective for identifying potential PPIs and could serve as a practical approach to aid bioexperiment in proteomics research.

Download Full-text

Complete Face Recovering: An Approach towards Recognizing a Person by a Single Partial Face Image without the Target Photo in Gallery

10.36227/techrxiv.12333176.v1 ◽

2020 ◽

Author(s):

Yiu-ming Cheung ◽

Mengke Li

Keyword(s):

Promising Result ◽

Face Image ◽

Attractive Potential ◽

Generative Adversarial Network ◽

Adversarial Network ◽

Discriminative Feature ◽

New Variant ◽

Potential Applications ◽

Benchmark Datasets

Complete face recovering (CFR) is to recover the complete face image of a given partial face image of a target person whose photo may not be included in the gallery set. The CFR has several attractive potential applications but is challenging. As far as we know, the CFR problem has yet to be explored in the literature. This paper therefore proposes an identity-preserved CFR approach (IP-CFR) to addressing the CFR. First, a denoising auto-encoder based network is applied to acquire the discriminative feature. Then, we propose an identity-preserved loss function to keep the personal identity information. Furthermore, the acquired features are fed into a new variant of the generative adversarial network (GAN) to restore the complete face image. In addition, a two-pathway discriminator is leveraged to enhance the quality of the recovered image. Experimental results on the benchmark datasets show the promising result of the proposed approach.

Download Full-text

Complete Face Recovering: An Approach towards Recognizing a Person by a Single Partial Face Image without the Target Photo in Gallery

10.36227/techrxiv.12333176 ◽

2020 ◽

Author(s):

Yiu-ming Cheung ◽

Mengke Li

Keyword(s):

Promising Result ◽

Face Image ◽

Attractive Potential ◽

Generative Adversarial Network ◽

Adversarial Network ◽

Discriminative Feature ◽

New Variant ◽

Potential Applications ◽

Benchmark Datasets

Download Full-text

Discriminative Center Loss for Face Photo-Sketch Recognition

10.21203/rs.3.rs-89691/v1 ◽

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.

Download Full-text

Joint Learning of the Center Points and Deep Metrics for Land-Use Classification in Remote Sensing

Remote Sensing ◽

10.3390/rs11010076 ◽

2019 ◽

Vol 11 (1) ◽

pp. 76 ◽

Cited By ~ 6

Author(s):

Zhiqiang Gong ◽

Ping Zhong ◽

Weidong Hu ◽

Yuming Hua

Keyword(s):

Remote Sensing ◽

Land Use ◽

Metric Learning ◽

Land Use Classification ◽

Training Process ◽

Pairwise Correlation ◽

Deep Model ◽

Training Samples ◽

Deep Metric Learning ◽

Learned Features

Deep learning methods, especially convolutional neural networks (CNNs), have shown remarkable ability for remote sensing scene classification. However, the traditional training process of standard CNNs only takes the point-wise penalization of the training samples into consideration, which usually makes the learned CNNs sub-optimal especially for remote sensing scenes with large intra-class variance and low inter-class variance. To address this problem, deep metric learning, which incorporates the metric learning into the deep model, is used to maximize the inter-class variance and minimize the intra-class variance for better representation. This work introduces structured metric learning for remote sensing scene representation, a special deep metric learning which can take full advantage of the training batch. However, the deep metrics only consider the pairwise correlation between the training samples, and ignores the classwise correlation from the class view. To take the classwise penalization into consideration, this work defines the center points of the learned features of each class in the training process to represent the class. Through increasing the variance between different center points and decreasing the variance between the learned features from each class and the corresponding center point, the representational ability can be further improved. Therefore, this work develops a novel center-based structured metric learning to take advantage of both the deep metrics and the center points. Finally, joint supervision of the cross-entropy loss and the center-based structured metric learning is developed for the land-use classification in remote sensing. It can joint learn the center points and the deep metrics to take advantage of the point-wise, the pairwise, and the classwise correlation. Experiments are conducted over three real-world remote sensing scene datasets, namely UC Merced Land-Use dataset, Brazilian Coffee Scene dataset, and Google dataset. The classification performance can achieve 97.30%, 91.24%, and 92.04% with the proposed method over the three datasets which are better than other state-of-the-art methods under the same experimental setups. The results demonstrate that the proposed method can improve the representational ability for the remote sensing scenes.

Download Full-text

Layer-Level Knowledge Distillation for Deep Neural Network Learning

Applied Sciences ◽

10.3390/app9101966 ◽

2019 ◽

Vol 9 (10) ◽

pp. 1966 ◽

Cited By ~ 1

Author(s):

Hao-Ting Li ◽

Shih-Chieh Lin ◽

Cheng-Yeh Chen ◽

Chen-Kuo Chiang

Keyword(s):

Structure Learning ◽

Superior Performance ◽

Gram Matrix ◽

Dual Model ◽

Feature Maps ◽

Model Learning ◽

Selection Scheme ◽

Neural Network Learning ◽

Learning Framework ◽

Deep Model

Motivated by the recently developed distillation approaches that aim to obtain small and fast-to-execute models, in this paper a novel Layer Selectivity Learning (LSL) framework is proposed for learning deep models. We firstly use an asymmetric dual-model learning framework, called Auxiliary Structure Learning (ASL), to train a small model with the help of a larger and well-trained model. Then, the intermediate layer selection scheme, called the Layer Selectivity Procedure (LSP), is exploited to determine the corresponding intermediate layers of source and target models. The LSP is achieved by two novel matrices, the layered inter-class Gram matrix and the inter-layered Gram matrix, to evaluate the diversity and discrimination of feature maps. The experimental results, demonstrated using three publicly available datasets, present the superior performance of model training using the LSL deep model learning framework.

Download Full-text

An Interpretation Architecture for Deep Learning Models with the Application of COVID-19 Diagnosis

Entropy ◽

10.3390/e23020204 ◽

2021 ◽

Vol 23 (2) ◽

pp. 204

Author(s):

Yuchai Wan ◽

Hongen Zhou ◽

Xun Zhang

Keyword(s):

Deep Learning ◽

Predictive Value ◽

Classification Performance ◽

Learning Approaches ◽

Learning Models ◽

Visual Interpretation ◽

Deep Model ◽

Diagnostic Decision ◽

Sensitivity Specificity ◽

Learned Features

The Coronavirus disease 2019 (COVID-19) has become one of the threats to the world. Computed tomography (CT) is an informative tool for the diagnosis of COVID-19 patients. Many deep learning approaches on CT images have been proposed and brought promising performance. However, due to the high complexity and non-transparency of deep models, the explanation of the diagnosis process is challenging, making it hard to evaluate whether such approaches are reliable. In this paper, we propose a visual interpretation architecture for the explanation of the deep learning models and apply the architecture in COVID-19 diagnosis. Our architecture designs a comprehensive interpretation about the deep model from different perspectives, including the training trends, diagnostic performance, learned features, feature extractors, the hidden layers, the support regions for diagnostic decision, and etc. With the interpretation architecture, researchers can make a comparison and explanation about the classification performance, gain insight into what the deep model learned from images, and obtain the supports for diagnostic decisions. Our deep model achieves the diagnostic result of 94.75%, 93.22%, 96.69%, 97.27%, and 91.88% in the criteria of accuracy, sensitivity, specificity, positive predictive value, and negative predictive value, which are 8.30%, 4.32%, 13.33%, 10.25%, and 6.19% higher than that of the compared traditional methods. The visualized features in 2-D and 3-D spaces provide the reasons for the superiority of our deep model. Our interpretation architecture would allow researchers to understand more about how and why deep models work, and can be used as interpretation solutions for any deep learning models based on convolutional neural network. It can also help deep learning methods to take a step forward in the clinical COVID-19 diagnosis field.

Download Full-text

Penggunaan Model Pembelajaran Somatic, Auditory, Visualization, Intellectualy (SAVI) dalam Peningkatan Hasil Belajar IPA tentang Organ Pencernaan Manusia Kelas V SD Negeri 3 Dorowati Tahun Ajaran 2020/2021

Kalam Cendekia: Jurnal Ilmiah Kependidikan ◽

10.20961/jkc.v9i2.46906 ◽

2021 ◽

Vol 9 (2) ◽

Author(s):

Rizki Isnaeni Putri ◽

Suhartono Suhartono ◽

Muhamad Chamdani

Keyword(s):

Learning Outcomes ◽

Natural Science ◽

Science Learning ◽

Concept Maps ◽

Digestive System ◽

Fifth Grade ◽

Model Learning ◽

Fifth Grade Students ◽

Training Stage ◽

Human Digestive System

The objectives of the research were: (1) to describe the steps of SAVI model in improving natural science learning outcomes, (2) to increase natural science learning outcomes about human digestive system, and (3) to describe the obstacles and solutions in applying SAVI model in improving natural science learning outcomes about human digestive system. The collaborative classroom action research was conducted in two cycles. The subjects were the teacher and 10 students of fifth grade of SDN 3 Dorowati. Data collection techniques were observation, interviews, and tests. The data validity used triangulation of techniques and triangulation of sources. The data analysis included data reduction, data presentation, and conclusions. The results indicated that: (1) the steps of Somatic, Auditory, Visualization, Intellectual (SAVI) model were: (a) preparation stage, (b) delivery stage, (c) training stage, and (d) final stage; (2) the application SAVI model improved natural science learning outcomes about human digestive system to fifth grade students of SDN 3 Dorowati in academic year of 2020/2021; (3) the obstacles were that many students did not cooperate in group discussions and found difficulties in making concept maps. The solutions were that the teacher guided the students to have discussion properly and helped the students in making concept maps.Keywords: Somatic, Auditory, Visualization, Intellectual (SAVI) model, learning outcomes, natural science

Download Full-text