scholarly journals Rectified Wing Loss for Efficient and Robust Facial Landmark Localisation with Convolutional Neural Networks

2019 ◽  
Vol 128 (8-9) ◽  
pp. 2126-2145 ◽  
Author(s):  
Zhen-Hua Feng ◽  
Josef Kittler ◽  
Muhammad Awais ◽  
Xiao-Jun Wu
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Loss Function ◽  
Data Augmentation ◽  
Small Sample Size ◽  
Small Sample ◽  
Imbalance Problem ◽  
Facial Landmark ◽  
The Impact ◽  
Coarse To Fine

AbstractEfficient and robust facial landmark localisation is crucial for the deployment of real-time face analysis systems. This paper presents a new loss function, namely Rectified Wing (RWing) loss, for regression-based facial landmark localisation with Convolutional Neural Networks (CNNs). We first systemically analyse different loss functions, including L2, L1 and smooth L1. The analysis suggests that the training of a network should pay more attention to small-medium errors. Motivated by this finding, we design a piece-wise loss that amplifies the impact of the samples with small-medium errors. Besides, we rectify the loss function for very small errors to mitigate the impact of inaccuracy of manual annotation. The use of our RWing loss boosts the performance significantly for regression-based CNNs in facial landmarking, especially for lightweight network architectures. To address the problem of under-representation of samples with large pose variations, we propose a simple but effective boosting strategy, referred to as pose-based data balancing. In particular, we deal with the data imbalance problem by duplicating the minority training samples and perturbing them by injecting random image rotation, bounding box translation and other data augmentation strategies. Last, the proposed approach is extended to create a coarse-to-fine framework for robust and efficient landmark localisation. Moreover, the proposed coarse-to-fine framework is able to deal with the small sample size problem effectively. The experimental results obtained on several well-known benchmarking datasets demonstrate the merits of our RWing loss and prove the superiority of the proposed method over the state-of-the-art approaches.

scholarly journals Graph Self Supervised Learning: the BT, the HSIC, and the VICReg

2021 ◽  
Author(s):  
Sayan Nag
Keyword(s):  
Neural Networks ◽  
Supervised Learning ◽  
Loss Function ◽  
Data Augmentation ◽  
Learning Strategy ◽  
Loss Functions ◽  
Augmentation Strategies ◽  
Batch Sizes ◽  
Graph Neural Networks ◽  
The Impact

Self-supervised learning and pre-training strategies have developed over the last few years especially for Convolutional Neural Networks (CNNs). Recently application of such methods can also be noticed for Graph Neural Networks (GNNs). In this paper, we have used a graph based self-supervised learning strategy with different loss functions (Barlow Twins[? ], HSIC[? ], VICReg[? ]) which have shown promising results when applied with CNNs previously. We have also proposed a hybrid loss function combining the advantages of VICReg and HSIC and called it as VICRegHSIC. The performance of these aforementioned methods have been compared when applied to two different datasets namely MUTAG and PROTEINS. Moreover, the impact of different batch sizes, projector dimensions and data augmentation strategies have also been explored. The results are preliminary and we will be continuing to explore with other datasets.

scholarly journals Detection of Falls from Non-Invasive Thermal Vision Sensors Using Convolutional Neural Networks

Proceedings ◽  
2018 ◽  
Vol 2 (19) ◽  
pp. 1236 ◽  
Author(s):  
Javier Quero ◽  
Matthew Burns ◽  
Muhammad Razzaq ◽  
Chris Nugent ◽  
Macarena Espinilla
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Data Augmentation ◽  
Low Cost ◽  
Non Invasive ◽  
Vision Sensors ◽  
Learning Capabilities ◽  
Augmentation Techniques ◽  
Thermal Vision ◽  
The Impact

In this work, we detail a methodology based on Convolutional Neural Networks (CNNs) to detect falls from non-invasive thermal vision sensors. First, we include an agile data collection to label images in order to create a dataset that describes several cases of single and multiple occupancy. These cases include standing inhabitants and target situations with a fallen inhabitant. Second, we provide data augmentation techniques to increase the learning capabilities of the classification and reduce the configuration time. Third, we have defined 3 types of CNN to evaluate the impact that the number of layers and kernel size have on the performance of the methodology. The results show an encouraging performance in single-occupancy contexts, with up to 92 % of accuracy, but a 10 % of reduction in accuracy in multiple-occupancy. The learning capabilities of CNNs have been highlighted due to the complex images obtained from the low-cost device. These images have strong noise as well as uncertain and blurred areas. The results highlight that the CNN based on 3-layers maintains a stable performance, as well as quick learning.

scholarly journals Accurate BAPL Score Classification of Brain PET Images Based on Convolutional Neural Networks with a Joint Discriminative Loss Function †

2020 ◽  
Vol 10 (3) ◽  
pp. 965 ◽  
Author(s):  
Ryosuke Sato ◽  
Yutaro Iwamoto ◽  
Kook Cho ◽  
Do-Young Kang ◽  
Yen-Wei Chen
Keyword(s):  
Alzheimer’S Disease ◽  
Neural Networks ◽  
Alzheimer's Disease ◽  
Image Classification ◽  
Convolutional Neural Networks ◽  
Loss Function ◽  
Data Augmentation ◽  
Natural Image ◽  
Deep Convolutional Neural Networks ◽  
Cerebral Disease

Alzheimer’s disease (AD) is an irreversible progressive cerebral disease with most of its symptoms appearing after 60 years of age. Alzheimer’s disease has been largely attributed to accumulation of amyloid beta (Aβ), but a complete cure has remained elusive. 18F-Florbetaben amyloid positron emission tomography (PET) has been shown as a more powerful tool for understanding AD-related brain changes than magnetic resonance imaging and computed tomography. In this paper, we propose an accurate classification method for scoring brain amyloid plaque load (BAPL) based on deep convolutional neural networks. A joint discriminative loss function was formulated by adding a discriminative intra-loss function to the conventional (cross-entropy) loss function. The performance of the proposed joint loss function was compared with that of the conventional loss function in three state-of-the-art deep neural network architectures. The intra-loss function significantly improved the BAPL classification performance. In addition, we showed that the mix-up data augmentation method, originally proposed for natural image classification, was also useful for medical image classification.

An influence of social isolation on the level of physical activity as well as on well-being and mental state of people during the coronavirus COVID-19 pandemic

2019 ◽  
Vol 129 (4) ◽  
pp. 127-131
Author(s):  
Agnieszka Parfin ◽  
Krystian Wdowiak ◽  
Marzena Furtak-Niczyporuk ◽  
Jolanta Herda
Keyword(s):  
Physical Activity ◽  
Social Isolation ◽  
Small Sample Size ◽  
Statistical Tests ◽  
Population Group ◽  
Well Being ◽  
Small Sample ◽  
Subjective Well Being ◽  
Tract Infections ◽  
The Impact

AbstractIntroduction. The COVID-19 is the name of an infectious disease caused by a new strain of coronavirus SARS-CoV-2 (Severe Acute Respiratory Syndrome Coronavirus 2). It was first diagnosed in December 2019 in patients in Wuhan City, Hubei Province, China. The symptoms are dominated by features of respiratory tract infections, in some patients with a very severe course leading to respiratory failure and, in extreme cases to death. Due to the spread of the infection worldwide, the WHO declared a pandemic in March 2020.Aim. An investigation of the impact of social isolation introduced due to the coronavirus pandemic on selected aspects of life. The researchers focused on observing changes in habits related to physical activity and their connections with people’s subjective well-being and emotional state.Material and methods. The study was carried out within the international project of the group „IRG on COVID and exercise”. The research tool was a standardized questionnaire.Results. Based on the data collected and the analysis of the percentage results, it can be observed that the overwhelming majority of people taking up physical activity reported a better mood during the pandemic. However, statistical tests do not confirm these relationships due to the small sample size.Conclusions. Isolation favours physical activity. Future, in-depth studies, by enlarging the population group, are necessary to confirm the above observations.

scholarly journals Data augmentation for computed tomography angiography via synthetic image generation and neural domain adaptation

2020 ◽  
Vol 6 (1) ◽  
Author(s):  
Malte Seemann ◽  
Lennart Bargsten ◽  
Alexander Schlaefer
Keyword(s):  
Computed Tomography ◽  
Neural Networks ◽  
Deep Learning ◽  
Medical Imaging ◽  
Computed Tomography Angiography ◽  
Data Augmentation ◽  
Domain Adaptation ◽  
Synthetic Image ◽  
Wide Range ◽  
The Impact

AbstractDeep learning methods produce promising results when applied to a wide range of medical imaging tasks, including segmentation of artery lumen in computed tomography angiography (CTA) data. However, to perform sufficiently, neural networks have to be trained on large amounts of high quality annotated data. In the realm of medical imaging, annotations are not only quite scarce but also often not entirely reliable. To tackle both challenges, we developed a two-step approach for generating realistic synthetic CTA data for the purpose of data augmentation. In the first step moderately realistic images are generated in a purely numerical fashion. In the second step these images are improved by applying neural domain adaptation. We evaluated the impact of synthetic data on lumen segmentation via convolutional neural networks (CNNs) by comparing resulting performances. Improvements of up to 5% in terms of Dice coefficient and 20% for Hausdorff distance represent a proof of concept that the proposed augmentation procedure can be used to enhance deep learning-based segmentation for artery lumen in CTA images.

scholarly journals The Role of Dopamine Receptor D2 in Bridging the Intention-Behavior Gap in Sport Participation

2021 ◽  
Vol 18 (5) ◽  
pp. 2379
Author(s):  
Seiyeong Park ◽  
Junhye Kwon ◽  
Chiyoung Ahn ◽  
Hae-Sung Cho ◽  
Hyo Youl Moon ◽  
...  
Keyword(s):  
University Students ◽  
Dopamine Receptor ◽  
Sport Participation ◽  
Small Sample Size ◽  
Behavioral Model ◽  
Small Sample ◽  
Male Students ◽  
Future Research ◽  
Dopamine Receptor D2 ◽  
The Impact

Previous studies have identified that a behavior can occur through the strongest predictor intention, but there is a gap between intention and behavior. Dopamine receptor D2 (DRD2) is known to account for a variance in sporting behaviors in human and animal subjects. However, the relationship between DRD2 and sport participation has been poorly studied, and the limited available reports are inconsistent. The present study was performed to examine the impact of DRD2 on sport participation among Korean university students based on the integrated behavioral model (IBM). Data were collected from enrolled university students in Seoul (N = 45). Participants answered survey questions first, and then they gave investigators their hair to provide DNA information (i.e., the A1 allele of DRD2). DRD2 had a significant effect on sport participation, but only in male students. Male students who carried the A1 allele of DRD2 significantly participated in 105.10 min more sporting activities than male students who did not. Moreover, the effect of intention on sport participation was significantly decreased when considering DRD2. Despite the small sample size, the results of this study could be a preliminary case for a larger study and indicate the direction of future research. Our results suggest that DRD2 may have played an important role as the “actual skill” shown in the IBM.

scholarly journals Data Augmentation Methods Applying Grayscale Images for Convolutional Neural Networks in Machine Vision

2021 ◽  
Vol 11 (15) ◽  
pp. 6721
Author(s):  
Jinyeong Wang ◽  
Sanghwan Lee
Keyword(s):  
Neural Networks ◽  
Machine Vision ◽  
Object Detection ◽  
Image Classification ◽  
Convolutional Neural Networks ◽  
Data Augmentation ◽  
Image Data ◽  
Manufacturing Productivity ◽  
Smart Factories ◽  
Grayscale Images

In increasing manufacturing productivity with automated surface inspection in smart factories, the demand for machine vision is rising. Recently, convolutional neural networks (CNNs) have demonstrated outstanding performance and solved many problems in the field of computer vision. With that, many machine vision systems adopt CNNs to surface defect inspection. In this study, we developed an effective data augmentation method for grayscale images in CNN-based machine vision with mono cameras. Our method can apply to grayscale industrial images, and we demonstrated outstanding performance in the image classification and the object detection tasks. The main contributions of this study are as follows: (1) We propose a data augmentation method that can be performed when training CNNs with industrial images taken with mono cameras. (2) We demonstrate that image classification or object detection performance is better when training with the industrial image data augmented by the proposed method. Through the proposed method, many machine-vision-related problems using mono cameras can be effectively solved by using CNNs.

Sign in / Sign up

Export Citation Format

Share Document