scholarly journals Ensemble-Based Out-of-Distribution Detection

Electronics ◽  
2021 ◽  
Vol 10 (5) ◽  
pp. 567
Author(s):  
Donghun Yang ◽  
Kien Mai Mai Ngoc ◽  
Iksoo Shin ◽  
Kyong-Ha Lee ◽  
Myunggwon Hwang
Keyword(s):  
Detection Method ◽  
State Of The Art ◽  
Metric Learning ◽  
Feature Space ◽  
Confidence Score ◽  
Distance Metric Learning ◽  
Current State ◽  
Overall Performance ◽  
Deep Learning Model

To design an efficient deep learning model that can be used in the real-world, it is important to detect out-of-distribution (OOD) data well. Various studies have been conducted to solve the OOD problem. The current state-of-the-art approach uses a confidence score based on the Mahalanobis distance in a feature space. Although it outperformed the previous approaches, the results were sensitive to the quality of the trained model and the dataset complexity. Herein, we propose a novel OOD detection method that can train more efficient feature space for OOD detection. The proposed method uses an ensemble of the features trained using the softmax-based classifier and the network based on distance metric learning (DML). Through the complementary interaction of these two networks, the trained feature space has a more clumped distribution and can fit well on the Gaussian distribution by class. Therefore, OOD data can be efficiently detected by setting a threshold in the trained feature space. To evaluate the proposed method, we applied our method to various combinations of image datasets. The results show that the overall performance of the proposed approach is superior to those of other methods, including the state-of-the-art approach, on any combination of datasets.

scholarly journals Smoothing additive manufactured parts using ns-pulsed laser radiation

2021 ◽  
Author(s):  
Florian Kuisat ◽  
Fernando Lasagni ◽  
Andrés Fabián Lasagni
Keyword(s):  
Surface Roughness ◽  
Mechanical Performance ◽  
State Of The Art ◽  
Pulsed Laser ◽  
Industrial Applications ◽  
Laser Source ◽  
Pulsed Laser Radiation ◽  
Current State ◽  
The Impact

AbstractIt is well known that the surface topography of a part can affect its mechanical performance, which is typical in additive manufacturing. In this context, we report about the surface modification of additive manufactured components made of Titanium 64 (Ti64) and Scalmalloy®, using a pulsed laser, with the aim of reducing their surface roughness. In our experiments, a nanosecond-pulsed infrared laser source with variable pulse durations between 8 and 200 ns was applied. The impact of varying a large number of parameters on the surface quality of the smoothed areas was investigated. The results demonstrated a reduction of surface roughness Sa by more than 80% for Titanium 64 and by 65% for Scalmalloy® samples. This allows to extend the applicability of additive manufactured components beyond the current state of the art and break new ground for the application in various industrial applications such as in aerospace.

scholarly journals Chi-Squared Distance Metric Learning for Histogram Data

2015 ◽  
Vol 2015 ◽  
pp. 1-12 ◽  
Author(s):  
Wei Yang ◽  
Luhui Xu ◽  
Xiaopan Chen ◽  
Fengbin Zheng ◽  
Yang Liu
Keyword(s):  
Nearest Neighbor ◽  
State Of The Art ◽  
Metric Learning ◽  
Nearest Neighbors ◽  
Distance Metric Learning ◽  
Distance Metric ◽  
Projected Gradient Method ◽  
Proper Distance ◽  
Chi Squared ◽  
Real World Datasets

Learning a proper distance metric for histogram data plays a crucial role in many computer vision tasks. The chi-squared distance is a nonlinear metric and is widely used to compare histograms. In this paper, we show how to learn a general form of chi-squared distance based on the nearest neighbor model. In our method, the margin of sample is first defined with respect to the nearest hits (nearest neighbors from the same class) and the nearest misses (nearest neighbors from the different classes), and then the simplex-preserving linear transformation is trained by maximizing the margin while minimizing the distance between each sample and its nearest hits. With the iterative projected gradient method for optimization, we naturally introduce thel2,1norm regularization into the proposed method for sparse metric learning. Comparative studies with the state-of-the-art approaches on five real-world datasets verify the effectiveness of the proposed method.

scholarly journals Deep Polarized Network for Supervised Learning of Accurate Binary Hashing Codes

2020 ◽  
Author(s):  
Lixin Fan ◽  
Kam Woh Ng ◽  
Ce Ju ◽  
Tianyu Zhang ◽  
Chee Seng Chan
Keyword(s):  
Large Deviations ◽  
Hamming Distance ◽  
State Of The Art ◽  
Metric Learning ◽  
Binary Codes ◽  
Distance Metric Learning ◽  
Learning Framework ◽  
Label Information ◽  
Learning To Hash ◽  
Random Codes

This paper proposes a novel deep polarized network (DPN) for learning to hash, in which each channel in the network outputs is pushed far away from zero by employing a differentiable bit-wise hinge-like loss which is dubbed as polarization loss. Reformulated within a generic Hamming Distance Metric Learning framework [Norouzi et al., 2012], the proposed polarization loss bypasses the requirement to prepare pairwise labels for (dis-)similar items and, yet, the proposed loss strictly bounds from above the pairwise Hamming Distance based losses. The intrinsic connection between pairwise and pointwise label information, as disclosed in this paper, brings about the following methodological improvements: (a) we may directly employ the proposed differentiable polarization loss with no large deviations incurred from the target Hamming distance based loss; and (b) the subtask of assigning binary codes becomes extremely simple --- even random codes assigned to each class suffice to result in state-of-the-art performances, as demonstrated in CIFAR10, NUS-WIDE and ImageNet100 datasets.

Modular Prosthetic Design for Transtibial Child Amputees

2017 ◽  
Author(s):  
Brendan M. Hickey ◽  
Samuel T. Woo ◽  
Sally F. Shady
Keyword(s):  
Quality Of Life ◽  
Health Care ◽  
Lower Limb ◽  
State Of The Art ◽  
Insurance Coverage ◽  
Review Article ◽  
Prosthetic Design ◽  
Current State ◽  
Limb Deficiencies

Lower limb deficiencies and below knee amputations are the most common form of deficiency that may arise from disease or trauma, and returning a patient close to a normal quality-of-life requires prosthetics, which can be quite challenging. Children present even further difficulty to prosthetists and physicians than adults. Although the underlying prosthetic principles for adults are the same for children, additional considerations must be made for practicality, such as downsizing while maintaining its degree of complexity, and frequent appointments to account for the rapid growth of an adolescent. This review article will evaluate the current state-of-the-art in the field of transtibial-amputee prosthetics, review the insurance coverage a typical family would face, and suggest potential improvements to children’s biomimetic prostheses that aid in reducing the frequency of health care provider intervention.

scholarly journals A review on the use of additive manufacturing to produce lower limb orthoses

2019 ◽  
Vol 5 (2) ◽  
pp. 85-94 ◽  
Author(s):  
Mohammed S. Alqahtani ◽  
Abdulsalam Al-Tamimi ◽  
Henrique Almeida ◽  
Glen Cooper ◽  
Paulo Bartolo
Keyword(s):  
Additive Manufacturing ◽  
Lower Limb ◽  
State Of The Art ◽  
Production Costs ◽  
Current State ◽  
Research Challenges ◽  
Fixation Devices ◽  
Alignment Correction ◽  
And Performance

Abstract Orthoses (exoskeletons and fracture fixation devices) enhance users’ ability to function and improve their quality of life by supporting alignment correction, restoring mobility, providing protection, immobilisation and stabilisation. Ideally, these devices should be personalised to each patient to improve comfort and performance. Production costs have been one of the main constraints for the production of personalised orthoses. However, customisation and personalisation of orthoses are now possible through the use of additive manufacturing. This paper presents the current state of the art of additive manufacturing for the fabrication of orthoses, providing several examples, and discusses key research challenges to be addressed to further develop this field.

scholarly journals Biomechanical behaviours of the bone–implant interface: a review

2019 ◽  
Vol 16 (156) ◽  
pp. 20190259 ◽  
Author(s):  
Xing Gao ◽  
Manon Fraulob ◽  
Guillaume Haïat
Keyword(s):  
Bone Tissue ◽  
Medical Devices ◽  
State Of The Art ◽  
Biomechanical Properties ◽  
Review Article ◽  
Implant Stability ◽  
Bone Implant ◽  
Current State ◽  
Mechanical Methods

In recent decades, cementless implants have been widely used in clinical practice to replace missing organs, to replace damaged or missing bone tissue or to restore joint functionality. However, there remain risks of failure which may have dramatic consequences. The success of an implant depends on its stability, which is determined by the biomechanical properties of the bone–implant interface (BII). The aim of this review article is to provide more insight on the current state of the art concerning the evolution of the biomechanical properties of the BII as a function of the implant's environment. The main characteristics of the BII and the determinants of implant stability are first introduced. Then, the different mechanical methods that have been employed to derive the macroscopic properties of the BII will be described. The experimental multi-modality approaches used to determine the microscopic biomechanical properties of periprosthetic newly formed bone tissue are also reviewed. Eventually, the influence of the implant's properties, in terms of both surface properties and biomaterials, is investigated. A better understanding of the phenomena occurring at the BII will lead to (i) medical devices that help surgeons to determine an implant's stability and (ii) an improvement in the quality of implants.

scholarly journals Dialogue Generation: From Imitation Learning to Inverse Reinforcement Learning

2019 ◽  
Vol 33 ◽  
pp. 6722-6729 ◽  
Author(s):  
Ziming Li ◽  
Julia Kiseleva ◽  
Maarten De Rijke
Keyword(s):  
Reinforcement Learning ◽  
State Of The Art ◽  
The State ◽  
Experimental Results ◽  
Imitation Learning ◽  
Local Optimum ◽  
Inverse Reinforcement Learning ◽  
High Quality ◽  
Overall Performance

The performance of adversarial dialogue generation models relies on the quality of the reward signal produced by the discriminator. The reward signal from a poor discriminator can be very sparse and unstable, which may lead the generator to fall into a local optimum or to produce nonsense replies. To alleviate the first problem, we first extend a recently proposed adversarial dialogue generation method to an adversarial imitation learning solution. Then, in the framework of adversarial inverse reinforcement learning, we propose a new reward model for dialogue generation that can provide a more accurate and precise reward signal for generator training. We evaluate the performance of the resulting model with automatic metrics and human evaluations in two annotation settings. Our experimental results demonstrate that our model can generate more high-quality responses and achieve higher overall performance than the state-of-the-art.

scholarly journals Mobile-PolypNet : Light-weight Colon Polyp Segmentation Network for Low Resources Settings

2021 ◽  
Author(s):  
Ranit Karmakar ◽  
Saeid Nooshabadi
Keyword(s):  
Deep Learning ◽  
State Of The Art ◽  
Colorectal Polyp ◽  
P Value ◽  
Colon Polyps ◽  
Current State ◽  
Model Size ◽  
Ablation Study ◽  
Small Clump ◽  
Deep Learning Model

Abstract Colon polyps, small clump of cells on the lining of the colon can lead to Colorectal cancer (CRC), one of the leading types of cancer globally. Hence, early detection of these polyps is crucial in the prevention of CRC. This paper proposes a lightweight deep learning model for colorectal polyp segmentation that achieved state-of-the-art accuracy while significantly reducing the model size and complexity. The proposed deep learning autoencoder model employs a set of state-of-the-art architectural blocks and optimization objective functions to achieve the desired efficiency. The model is trained and tested on five publicly available colorectal polyp segmentation datasets (CVC-ClinicDB, CVC-ColonDB, EndoScene, Kvasir, and ETIS). We also performed ablation testing on the model to test various aspects of the autoencoder architecture. We performed the model evaluation using most of the common image segmentation metrics. The backbone model achieved a dice score of 0.935 on the Kvasir dataset and 0.945 on the CVC-ClinicDB dataset improving the accuracy by 4.12% and 5.12% respectively over the current state-of-the-art network, while using 88 times fewer parameters, 40 times less storage space, and being computationally 17 times more efficient. Our ablation study showed that the addition of ConvSkip in the autoencoder slightly improves the model’s performance but it was not significant (p-value=0.815).

What Every Therapist Needs to Know About Couple Therapy

2019 ◽  
Vol 36 (3) ◽  
pp. 121-142 ◽  
Author(s):  
W. Kim Halford ◽  
Christopher A. Pepping
Keyword(s):  
Couple Therapy ◽  
State Of The Art ◽  
Couple Relationship ◽  
Couple Relationships ◽  
Art And Science ◽  
Relationship Distress ◽  
Relationship Problems ◽  
Current State ◽  
The Relationship

AbstractThis invited paper is a review of the significance of couple relationships to the practice of all therapists. The article begins with a summary of the evidence on the centrality of committed couple relationships to the lives and wellbeing of adults, and the association of the quality of the parents’ couple relationship on the wellbeing of children. We argue that the well-established reciprocal association between individual problems and couple relationship problems means that all therapists need to pay attention to how a couple relationship might be influencing a client's functioning, even if the relationship is not the presenting problem. There is an outline the evolution of current approaches to behavioural couple therapy, and the current state of the art and science of couple therapy. We present an analysis of the evidence for couple therapy as a treatment for relationship distress, as well as couple-based treatments for individual problems. This is followed by a description of the distinctive challenges in working with couples and how to address those challenges, and recommendations about how to address the needs of diverse couple relationships. Finally, we propose some core therapist competencies needed to work effectively with couples.

Sign in / Sign up

Export Citation Format

Share Document