Deep Active Context Estimation for Automated COVID-19 Diagnosis

2021 ◽  
Vol 17 (3s) ◽  
pp. 1-22
Author(s):  
Bingzhi Chen ◽  
Yishu Liu ◽  
Zheng Zhang ◽  
Yingjian Li ◽  
Zhao Zhang ◽  
...  
Keyword(s):  
Large Scale ◽  
State Of The Art ◽  
Superior Performance ◽  
High Confidence ◽  
Content Type ◽  
Feature Representations ◽  
Spatial Dependencies ◽  
Channel Interactions ◽  
Symptoms And Signs ◽  
Ct Slices

Many studies on automated COVID-19 diagnosis have advanced rapidly with the increasing availability of large-scale CT annotated datasets. Inevitably, there are still a large number of unlabeled CT slices in the existing data sources since it requires considerable consuming labor efforts. Notably, cinical experience indicates that the neighboring CT slices may present similar symptoms and signs. Inspired by such wisdom, we propose DACE, a novel CNN-based deep active context estimation framework, which leverages the unlabeled neighbors to progressively learn more robust feature representations and generate a well-performed classifier for COVID-19 diagnosis. Specifically, the backbone of the proposed DACE framework is constructed by a well-designed Long-Short Hierarchical Attention Network (LSHAN), which effectively incorporates two complementary attention mechanisms, i.e., short-range channel interactions (SCI) module and long-range spatial dependencies (LSD) module, to learn the most discriminative features from CT slices. To make full use of such available data, we design an efficient context estimation criterion to carefully assign the additional labels to these neighbors. Benefiting from two complementary types of informative annotations from -nearest neighbors, i.e., the majority of high-confidence samples with pseudo labels and the minority of low-confidence samples with hand-annotated labels, the proposed LSHAN can be fine-tuned and optimized in an incremental learning manner. Extensive experiments on the Clean-CC-CCII dataset demonstrate the superior performance of our method compared with the state-of-the-art baselines.

scholarly journals Non-Local Context Encoder: Robust Biomedical Image Segmentation against Adversarial Attacks

2019 ◽  
Vol 33 ◽  
pp. 8417-8424 ◽  
Author(s):  
Xiang He ◽  
Sibei Yang ◽  
Guanbin Li ◽  
Haofeng Li ◽  
Huiyou Chang ◽  
...  
Keyword(s):  
Image Segmentation ◽  
State Of The Art ◽  
Contextual Information ◽  
Local Context ◽  
Deep Convolutional Neural Networks ◽  
Biomedical Image ◽  
Feature Representations ◽  
Segmentation Methods ◽  
Spatial Dependencies ◽  
Non Local

Recent progress in biomedical image segmentation based on deep convolutional neural networks (CNNs) has drawn much attention. However, its vulnerability towards adversarial samples cannot be overlooked. This paper is the first one that discovers that all the CNN-based state-of-the-art biomedical image segmentation models are sensitive to adversarial perturbations. This limits the deployment of these methods in safety-critical biomedical fields. In this paper, we discover that global spatial dependencies and global contextual information in a biomedical image can be exploited to defend against adversarial attacks. To this end, non-local context encoder (NLCE) is proposed to model short- and long-range spatial dependencies and encode global contexts for strengthening feature activations by channel-wise attention. The NLCE modules enhance the robustness and accuracy of the non-local context encoding network (NLCEN), which learns robust enhanced pyramid feature representations with NLCE modules, and then integrates the information across different levels. Experiments on both lung and skin lesion segmentation datasets have demonstrated that NLCEN outperforms any other state-of-the-art biomedical image segmentation methods against adversarial attacks. In addition, NLCE modules can be applied to improve the robustness of other CNN-based biomedical image segmentation methods.

Large-scale economic load dispatch using squirrel search algorithm

2020 ◽  
Vol 14 (6) ◽  
pp. 1351-1380
Author(s):  
Sakthivel V.P. ◽  
Suman M. ◽  
Sathya P.D.
Keyword(s):  
Power Plants ◽  
Large Scale ◽  
Optimization Problems ◽  
Search Algorithm ◽  
Optimization Technique ◽  
Research Work ◽  
Superior Performance ◽  
Economic Load Dispatch ◽  
Fuel Cost ◽  
Content Type

Purpose Economic load dispatch (ELD) is one of the crucial optimization problems in power system planning and operation. The ELD problem with valve point loading (VPL) and multi-fuel options (MFO) is defined as a non-smooth and non-convex optimization problem with equality and inequality constraints, which obliges an efficient heuristic strategy to be addressed. The purpose of this study is to present a new and powerful heuristic optimization technique (HOT) named as squirrel search algorithm (SSA) to solve non-convex ELD problems of large-scale power plants. Design/methodology/approach The suggested SSA approach is aimed to minimize the total fuel cost consumption of power plant considering their generation values as decision variables while satisfying the problem constraints. It confers a solution to the ELD issue by anchoring with foraging behavior of squirrels based on the dynamic jumping and gliding strategies. Furthermore, a heuristic approach and selection rules are used in SSA to handle the constraints appropriately. Findings Empirical results authenticate the superior performance of SSA technique by validating on four different large-scale systems. Comparing SSA with other HOTs, numerical results depict its proficiencies with high-qualitative solution and by its excellent computational efficiency to solve the ELD problems with non-smooth fuel cost function addressing the VPL and MFO. Moreover, the non-parametric tests prove the robustness and efficacy of the suggested SSA and demonstrate that it can be used as a competent optimizer for solving the real-world large-scale non-convex ELD problems. Practical implications This study has compared various HOTs to determine optimal generation scheduling for large-scale ELD problems. Consequently, its comparative analysis will be beneficial to power engineers for accurate generation planning. Originality/value To the best of the authors’ knowledge, this manuscript is the first research work of using SSA approach for solving ELD problems. Consequently, the solution to this problem configures the key contribution of this paper.

scholarly journals CharTeC-Net: An Efficient and Lightweight Character-Based Convolutional Network for Text Classification

2020 ◽  
Vol 2020 ◽  
pp. 1-7 ◽  
Author(s):  
Aboubakar Nasser Samatin Njikam ◽  
Huan Zhao
Keyword(s):  
Text Classification ◽  
Building Block ◽  
Large Scale ◽  
State Of The Art ◽  
Building Blocks ◽  
Training Data ◽  
Superior Performance ◽  
Classification Problems ◽  
Computationally Efficient ◽  
Convolutional Network

This paper introduces an extremely lightweight (with just over around two hundred thousand parameters) and computationally efficient CNN architecture, named CharTeC-Net (Character-based Text Classification Network), for character-based text classification problems. This new architecture is composed of four building blocks for feature extraction. Each of these building blocks, except the last one, uses 1 × 1 pointwise convolutional layers to add more nonlinearity to the network and to increase the dimensions within each building block. In addition, shortcut connections are used in each building block to facilitate the flow of gradients over the network, but more importantly to ensure that the original signal present in the training data is shared across each building block. Experiments on eight standard large-scale text classification and sentiment analysis datasets demonstrate CharTeC-Net’s superior performance over baseline methods and yields competitive accuracy compared with state-of-the-art methods, although CharTeC-Net has only between 181,427 and 225,323 parameters and weighs less than 1 megabyte.

Learning strategies for competence development in enterprises

2017 ◽  
Vol 49 (1) ◽  
pp. 1-5
Author(s):  
Ulrik Brandi ◽  
Rosa Lisa Iannone
Keyword(s):  
Human Resources ◽  
Learning Strategies ◽  
Design Methodology ◽  
Large Scale ◽  
State Of The Art ◽  
Competence Development ◽  
Abductive Reasoning ◽  
Structured Interviews ◽  
Content Type ◽  
Enterprise Level

Purpose The purpose of this paper is to examine learning strategies for competence development at the enterprise level, and how these can be actualised in practice. The authors focus on three influential aspects, namely: the highest valued employee skills, main triggers for learning and investment in learning, as well as the most successful types of learning. Design/methodology/approach The empirical research was designed according to abductive reasoning. The data draw on research we undertook between 2013 and 2015, including semi-structured interviews with management, human resources and union representatives, as well as questionnaire responses from a total of 31 EU and 163 EU-competitors, across 53 industries and 22 countries. Findings Competence development requires flexible, learner-centred strategies for initiatives that respond to immediate business needs. Additionally, despite soft competences being so highly valued and sought after, investment (financial and other) by enterprises in developing them is low, relative to the investments poured into hard competences. Also, there is a clear employee demand gap for learning that develops soft competences. Originality/value Findings and recommendations are based on a large-scale empirical study, providing state-of-the-art knowledge, upon which we can renew our current learning strategies in workplaces.

scholarly journals Discriminative Deep Hashing for Scalable Face Image Retrieval

2017 ◽  
Author(s):  
Jie Lin ◽  
Zechao Li ◽  
Jinhui Tang
Keyword(s):  
Image Retrieval ◽  
Large Scale ◽  
State Of The Art ◽  
Face Image ◽  
Superior Performance ◽  
Prediction Errors ◽  
Unified Framework ◽  
Multi Scale ◽  
Deep Hashing ◽  
Hash Codes

With the explosive growth of images containing faces, scalable face image retrieval has attracted increasing attention. Due to the amazing effectiveness, deep hashing has become a popular hashing method recently. In this work, we propose a new Discriminative Deep Hashing (DDH) network to learn discriminative and compact hash codes for large-scale face image retrieval. The proposed network incorporates the end-to-end learning, the divide-and-encode module and the desired discrete code learning into a unified framework. Specifically, a network with a stack of convolution-pooling layers is proposed to extract multi-scale and robust features by merging the outputs of the third max pooling layer and the fourth convolutional layer. To reduce the redundancy among hash codes and the network parameters simultaneously, a divide-and-encode module to generate compact hash codes. Moreover, a loss function is introduced to minimize the prediction errors of the learned hash codes, which can lead to discriminative hash codes. Extensive experiments on two datasets demonstrate that the proposed method achieves superior performance compared with some state-of-the-art hashing methods.

An evolutionary based framework for many-objective optimization problems

2018 ◽  
Vol 35 (4) ◽  
pp. 1805-1828 ◽  
Author(s):  
Kimia Bazargan Lari ◽  
Ali Hamzeh
Keyword(s):  
Optimization Problems ◽  
State Of The Art ◽  
Fitness Function ◽  
Population Diversity ◽  
Numerical Results ◽  
Superior Performance ◽  
High Dimensional ◽  
Test Problems ◽  
Content Type ◽  
Objective Space

Purpose Recently, many-objective optimization evolutionary algorithms have been the main issue for researchers in the multi-objective optimization community. To deal with many-objective problems (typically for four or more objectives) some modern frameworks are proposed which have the potential of achieving the finest non-dominated solutions in many-objective spaces. The effectiveness of these algorithms deteriorates greatly as the problem’s dimension increases. Diversity reduction in the objective space is the main reason of this phenomenon. Design/methodology/approach To properly deal with this undesirable situation, this work introduces an indicator-based evolutionary framework that can preserve the population diversity by producing a set of discriminated solutions in high-dimensional objective space. This work attempts to diversify the objective space by proposing a fitness function capable of discriminating the chromosomes in high-dimensional space. The numerical results prove the potential of the proposed method, which had superior performance in most of test problems in comparison with state-of-the-art algorithms. Findings The achieved numerical results empirically prove the superiority of the proposed method to state-of-the-art counterparts in the most test problems of a known artificial benchmark. Originality/value This paper provides a new interpretation and important insights into the many-objective optimization realm by emphasizing on preserving the population diversity.

Understanding the cultural concerns of libraries based on automatic image analysis

2019 ◽  
Vol 37 (3) ◽  
pp. 419-434
Author(s):  
Heng Ding ◽  
Wei Lu ◽  
Tingting Jiang
Keyword(s):  
Exploratory Study ◽  
Design Methodology ◽  
Large Scale ◽  
State Of The Art ◽  
Automatic Analysis ◽  
Automatic Image Analysis ◽  
Content Type ◽  
Image Dataset ◽  
Learning Technique ◽  
Semantic Concepts

Purpose Photographs are a kind of cultural heritage and very useful for cultural and historical studies. However, traditional or manual research methods are costly and cannot be applied on a large scale. This paper aims to present an exploratory study for understanding the cultural concerns of libraries based on the automatic analysis of large-scale image collections. Design/methodology/approach In this work, an image dataset including 85,023 images preserved and shared by 28 libraries is collected from the Flickr Commons project. Then, a method is proposed for representing the culture with a distribution of visual semantic concepts using a state-of-the-art deep learning technique and measuring the cultural concerns of image collections using two metrics. Case studies on this dataset demonstrated the great potential and promise of the method for understanding large-scale image collections from the perspective of cultural concerns. Findings The proposed method has the ability to discover important cultural units from large-scale image collections. The proposed two metrics are able to quantify the cultural concerns of libraries from different perspectives. Originality/value To the best of the authors’ knowledge, this is the first automatic analysis of images for the purpose of understanding cultural concerns of libraries. The significance of this study mainly consists in the proposed method of understanding the cultural concerns of libraries based on the automatic analysis of the visual semantic concepts in image collections. Moreover, this paper has examined the cultural concerns (e.g. important cultural units, cultural focus, trends and volatility of cultural concerns) of 28 libraries.

scholarly journals Rethinking the Fourier-Mellin Transform: Multiple Depths in the Camera’s View

2021 ◽  
Vol 13 (5) ◽  
pp. 1000
Author(s):  
Qingwen Xu ◽  
Haofei Kuang ◽  
Laurent Kneip ◽  
Sören Schwertfeger
Keyword(s):  
Remote Sensing ◽  
Large Scale ◽  
Feature Detection ◽  
Mellin Transform ◽  
State Of The Art ◽  
Visual Odometry ◽  
Superior Performance ◽  
Fourier Mellin Transform ◽  
And Robotics ◽  
Better Than

Remote sensing and robotics often rely on visual odometry (VO) for localization. Many standard approaches for VO use feature detection. However, these methods will meet challenges if the environments are feature-deprived or highly repetitive. Fourier-Mellin Transform (FMT) is an alternative VO approach that has been shown to show superior performance in these scenarios and is often used in remote sensing. One limitation of FMT is that it requires an environment that is equidistant to the camera, i.e., single-depth. To extend the applications of FMT to multi-depth environments, this paper presents the extended Fourier-Mellin Transform (eFMT), which maintains the advantages of FMT with respect to feature-deprived scenarios. To show the robustness and accuracy of eFMT, we implement an eFMT-based visual odometry framework and test it in toy examples and a large-scale drone dataset. All these experiments are performed on data collected in challenging scenarios, such as, trees, wooden boards and featureless roofs. The results show that eFMT performs better than FMT in the multi-depth settings. Moreover, eFMT also outperforms state-of-the-art VO algorithms, such as ORB-SLAM3, SVO and DSO, in our experiments.

scholarly journals 3D Human Pose Estimation via Explicit Compositional Depth Maps

2020 ◽  
Vol 34 (07) ◽  
pp. 12378-12385
Author(s):  
Haiping Wu ◽  
Bin Xiao
Keyword(s):  
Large Scale ◽  
State Of The Art ◽  
Superior Performance ◽  
Projection Model ◽  
Depth Maps ◽  
3D Camera ◽  
Camera Perspective ◽  
Monocular Image ◽  
Human Pose ◽  
Body Joints

In this work, we tackle the problem of estimating 3D human pose in camera space from a monocular image. First, we propose to use densely-generated limb depth maps to ease the learning of body joints depth, which are well aligned with image cues. Then, we design a lifting module from 2D pixel coordinates to 3D camera coordinates which explicitly takes the depth values as inputs, and is aligned with camera perspective projection model. We show our method achieves superior performance on large-scale 3D pose datasets Human3.6M and MPI-INF-3DHP, and sets the new state-of-the-art.

scholarly journals Large-Scale Visual Relationship Understanding

2019 ◽  
Vol 33 ◽  
pp. 9185-9194 ◽  
Author(s):  
Ji Zhang ◽  
Yannis Kalantidis ◽  
Marcus Rohrbach ◽  
Manohar Paluri ◽  
Ahmed Elgammal ◽  
...  
Keyword(s):  
Large Scale ◽  
State Of The Art ◽  
Scale Up ◽  
Superior Performance ◽  
Matched Pairs ◽  
Detection Model ◽  
Large Numbers ◽  
Shared Space ◽  
Visual Understanding ◽  
Genome Dataset

Large scale visual understanding is challenging, as it requires a model to handle the widely-spread and imbalanced distribution of 〈subject, relation, object〉 triples. In real-world scenarios with large numbers of objects and relations, some are seen very commonly while others are barely seen. We develop a new relationship detection model that embeds objects and relations into two vector spaces where both discriminative capability and semantic affinity are preserved. We learn a visual and a semantic module that map features from the two modalities into a shared space, where matched pairs of features have to discriminate against those unmatched, but also maintain close distances to semantically similar ones. Benefiting from that, our model can achieve superior performance even when the visual entity categories scale up to more than 80,000, with extremely skewed class distribution. We demonstrate the efficacy of our model on a large and imbalanced benchmark based of Visual Genome that comprises 53,000+ objects and 29,000+ relations, a scale at which no previous work has been evaluated at. We show superiority of our model over competitive baselines on the original Visual Genome dataset with 80,000+ categories. We also show state-of-the-art performance on the VRD dataset and the scene graph dataset which is a subset of Visual Genome with 200 categories.

Sign in / Sign up

Export Citation Format

Share Document