On Loss Functions for Deep-Learning Based T60 Estimation

2021 ◽  
Author(s):  
Yuying Li ◽  
Yuchen Liu ◽  
Donald S. Williamson
Keyword(s):  
Deep Learning ◽  
Loss Functions

scholarly journals Study on Radar Echo-Filling in an Occlusion Area by a Deep Learning Algorithm

2021 ◽  
Vol 13 (9) ◽  
pp. 1779
Author(s):  
Xiaoyan Yin ◽  
Zhiqun Hu ◽  
Jiafeng Zheng ◽  
Boyong Li ◽  
Yuanyuan Zuo
Keyword(s):  
Deep Learning ◽  
Loss Function ◽  
Learning Algorithm ◽  
Weather Radar ◽  
Loss Functions ◽  
Training Dataset ◽  
Echo Intensity ◽  
Common Mean ◽  
Deep Learning Algorithm ◽  
Radar Beam

Radar beam blockage is an important error source that affects the quality of weather radar data. An echo-filling network (EFnet) is proposed based on a deep learning algorithm to correct the echo intensity under the occlusion area in the Nanjing S-band new-generation weather radar (CINRAD/SA). The training dataset is constructed by the labels, which are the echo intensity at the 0.5° elevation in the unblocked area, and by the input features, which are the intensity in the cube including multiple elevations and gates corresponding to the location of bottom labels. Two loss functions are applied to compile the network: one is the common mean square error (MSE), and the other is a self-defined loss function that increases the weight of strong echoes. Considering that the radar beam broadens with distance and height, the 0.5° elevation scan is divided into six range bands every 25 km to train different models. The models are evaluated by three indicators: explained variance (EVar), mean absolute error (MAE), and correlation coefficient (CC). Two cases are demonstrated to compare the effect of the echo-filling model by different loss functions. The results suggest that EFnet can effectively correct the echo reflectivity and improve the data quality in the occlusion area, and there are better results for strong echoes when the self-defined loss function is used.

scholarly journals Assessing the Impact of the Loss Function, Architecture and Image Type for Deep Learning-Based Wildfire Segmentation

2021 ◽  
Vol 11 (15) ◽  
pp. 7046
Author(s):  
Jorge Francisco Ciprián-Sánchez ◽  
Gilberto Ochoa-Ruiz ◽  
Lucile Rossi ◽  
Frédéric Morandini
Keyword(s):  
Deep Learning ◽  
Loss Function ◽  
State Of The Art ◽  
Fire Detection ◽  
Loss Functions ◽  
Wildfire Spread ◽  
Combine Information ◽  
The Impact ◽  
Image Type ◽  
Segmentation Models

Wildfires stand as one of the most relevant natural disasters worldwide, particularly more so due to the effect of climate change and its impact on various societal and environmental levels. In this regard, a significant amount of research has been done in order to address this issue, deploying a wide variety of technologies and following a multi-disciplinary approach. Notably, computer vision has played a fundamental role in this regard. It can be used to extract and combine information from several imaging modalities in regard to fire detection, characterization and wildfire spread forecasting. In recent years, there has been work pertaining to Deep Learning (DL)-based fire segmentation, showing very promising results. However, it is currently unclear whether the architecture of a model, its loss function, or the image type employed (visible, infrared, or fused) has the most impact on the fire segmentation results. In the present work, we evaluate different combinations of state-of-the-art (SOTA) DL architectures, loss functions, and types of images to identify the parameters most relevant to improve the segmentation results. We benchmark them to identify the top-performing ones and compare them to traditional fire segmentation techniques. Finally, we evaluate if the addition of attention modules on the best performing architecture can further improve the segmentation results. To the best of our knowledge, this is the first work that evaluates the impact of the architecture, loss function, and image type in the performance of DL-based wildfire segmentation models.

scholarly journals Assembly Quality Detection Based on Class-Imbalanced Semi-Supervised Learning

2021 ◽  
Vol 11 (21) ◽  
pp. 10373
Author(s):  
Zichen Lu ◽  
Jiabin Jiang ◽  
Pin Cao ◽  
Yongying Yang
Keyword(s):  
Deep Learning ◽  
Supervised Learning ◽  
Class Imbalance ◽  
Loss Functions ◽  
Quality Inspection ◽  
Data Annotation ◽  
Quality Detection ◽  
High Classification Accuracy ◽  
Total Data ◽  
The Mean

Due to the imperfect assembly process, the unqualified assembly of a missing gasket or lead seal will affect the product’s performance and possibly cause safety accidents. Machine vision method based on deep learning has been widely used in quality inspection. Semi-supervised learning (SSL) has been applied in training deep learning models to reduce the burden of data annotation. The dataset obtained from the production line tends to be class-imbalanced because the assemblies are qualified in most cases. However, most SSL methods suffer from lower performance in class-imbalanced datasets. Therefore, we propose a new semi-supervised algorithm that achieves high classification accuracy on the class-imbalanced assembly dataset with limited labeled data. Based on the mean teacher algorithm, the proposed algorithm uses certainty to select reliable teacher predictions for student learning dynamically, and loss functions are modified to improve the model’s robustness against class imbalance. Results show that when only 10% of the total data are labeled, and the imbalance rate is 5.3, the proposed method can improve the accuracy from 85.34% to 93.67% compared to supervised learning. When the amount of annotated data accounts for 20%, the accuracy can reach 98.83%.

scholarly journals Eigenloss: Combined PCA-Based Loss Function for Polyp Segmentation

Mathematics ◽  
2020 ◽  
Vol 8 (8) ◽  
pp. 1316
Author(s):  
Luisa F. Sánchez-Peralta ◽  
Artzai Picón ◽  
Juan Antonio Antequera-Barroso ◽  
Juan Francisco Ortega-Morán ◽  
Francisco M. Sánchez-Margallo ◽  
...  
Keyword(s):  
Deep Learning ◽  
Loss Function ◽  
Survival Rates ◽  
Principal Component ◽  
Loss Functions ◽  
Cancer Death ◽  
Linear Combinations ◽  
The Individual ◽  
Deep Learning Model ◽  
Death Causes

Colorectal cancer is one of the leading cancer death causes worldwide, but its early diagnosis highly improves the survival rates. The success of deep learning has also benefited this clinical field. When training a deep learning model, it is optimized based on the selected loss function. In this work, we consider two networks (U-Net and LinkNet) and two backbones (VGG-16 and Densnet121). We analyzed the influence of seven loss functions and used a principal component analysis (PCA) to determine whether the PCA-based decomposition allows for the defining of the coefficients of a non-redundant primal loss function that can outperform the individual loss functions and different linear combinations. The eigenloss is defined as a linear combination of the individual losses using the elements of the eigenvector as coefficients. Empirical results show that the proposed eigenloss improves the general performance of individual loss functions and outperforms other linear combinations when Linknet is used, showing potential for its application in polyp segmentation problems.

scholarly journals Deep Learning with Dynamically Weighted Loss Function for Sensor-Based Prognostics and Health Management

Sensors ◽  
2020 ◽  
Vol 20 (3) ◽  
pp. 723 ◽  
Author(s):  
Divish Rengasamy ◽  
Mina Jafari ◽  
Benjamin Rothwell ◽  
Xin Chen ◽  
Grazziela P. Figueredo
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Loss Function ◽  
Short Term Memory ◽  
Health Management ◽  
Remaining Useful Life ◽  
Loss Functions ◽  
Pressure System ◽  
Failure Data ◽  
Prognostic And Health Management

Deep learning has been employed to prognostic and health management of automotive and aerospace with promising results. Literature in this area has revealed that most contributions regarding deep learning is largely focused on the model’s architecture. However, contributions regarding improvement of different aspects in deep learning, such as custom loss function for prognostic and health management are scarce. There is therefore an opportunity to improve upon the effectiveness of deep learning for the system’s prognostics and diagnostics without modifying the models’ architecture. To address this gap, the use of two different dynamically weighted loss functions, a newly proposed weighting mechanism and a focal loss function for prognostics and diagnostics task are investigated. A dynamically weighted loss function is expected to modify the learning process by augmenting the loss function with a weight value corresponding to the learning error of each data instance. The objective is to force deep learning models to focus on those instances where larger learning errors occur in order to improve their performance. The two loss functions used are evaluated using four popular deep learning architectures, namely, deep feedforward neural network, one-dimensional convolutional neural network, bidirectional gated recurrent unit and bidirectional long short-term memory on the commercial modular aero-propulsion system simulation data from NASA and air pressure system failure data for Scania trucks. Experimental results show that dynamically-weighted loss functions helps us achieve significant improvement for remaining useful life prediction and fault detection rate over non-weighted loss function predictions.

scholarly journals A Strong and Efficient Baseline for Vehicle Re-Identification Using Deep Triplet Embedding

2020 ◽  
Vol 10 (1) ◽  
pp. 27-45 ◽  
Author(s):  
Ratnesh Kumar ◽  
Edwin Weill ◽  
Farzin Aghdasi ◽  
Parthasarathy Sriram
Keyword(s):  
Deep Learning ◽  
Smart City ◽  
State Of The Art ◽  
Loss Functions ◽  
Camera Network ◽  
Formal Evaluation ◽  
Cross Domain ◽  
Extensive Evaluation ◽  
Data Points ◽  
Triplet Loss

AbstractIn this paper we tackle the problem of vehicle re-identification in a camera network utilizing triplet embeddings. Re-identification is the problem of matching appearances of objects across different cameras. With the proliferation of surveillance cameras enabling smart and safer cities, there is an ever-increasing need to re-identify vehicles across cameras. Typical challenges arising in smart city scenarios include variations of viewpoints, illumination and self occlusions. Most successful approaches for re-identification involve (deep) learning an embedding space such that the vehicles of same identities are projected closer to one another, compared to the vehicles representing different identities. Popular loss functions for learning an embedding (space) include contrastive or triplet loss. In this paper we provide an extensive evaluation of triplet loss applied to vehicle re-identification and demonstrate that using the recently proposed sampling approaches for mining informative data points outperform most of the existing state-of-the-art approaches for vehicle re-identification. Compared to most existing state-of-the-art approaches, our approach is simpler and more straightforward for training utilizing only identity-level annotations, along with one of the smallest published embedding dimensions for efficient inference. Furthermore in this work we introduce a formal evaluation of a triplet sampling variant (batch sample) into the re-identification literature. In addition to the conference version [24], this submission adds extensive experiments on new released datasets, cross domain evaluations and ablation studies.

scholarly journals Data-driven prediction of unsteady flow over a circular cylinder using deep learning

2019 ◽  
Vol 879 ◽  
pp. 217-254 ◽  
Author(s):  
Sangseung Lee ◽  
Donghyun You
Keyword(s):  
Deep Learning ◽  
Circular Cylinder ◽  
Unsteady Flow ◽  
Conservation Laws ◽  
Flow Fields ◽  
Loss Functions ◽  
Generative Adversarial Networks ◽  
Learning Networks ◽  
Adversarial Networks ◽  
Adversarial Training

Unsteady flow fields over a circular cylinder are used for training and then prediction using four different deep learning networks: generative adversarial networks with and without consideration of conservation laws; and convolutional neural networks with and without consideration of conservation laws. Flow fields at future occasions are predicted based on information on flow fields at previous occasions. Predictions of deep learning networks are made for flow fields at Reynolds numbers that were not used during training. Physical loss functions are proposed to explicitly provide information on conservation of mass and momentum to deep learning networks. An adversarial training is applied to extract features of flow dynamics in an unsupervised manner. Effects of the proposed physical loss functions and adversarial training on predicted results are analysed. Captured and missed flow physics from predictions are also analysed. Predicted flow fields using deep learning networks are in good agreement with flow fields computed by numerical simulations.

Performance Analysis of GAN Architecture for Effective Facial Expression Synthesis

2021 ◽  
pp. 290-316
Author(s):  
Karthik R. ◽  
Nandana B. ◽  
Mayuri Patil ◽  
Chandreyee Basu ◽  
Vijayarajan R.
Keyword(s):  
Deep Learning ◽  
Performance Analysis ◽  
Facial Expressions ◽  
Data Distribution ◽  
Loss Functions ◽  
Human Beings ◽  
Learning Networks ◽  
Open Mouth ◽  
Important Means

Facial expressions are an important means of communication among human beings, as they convey different meanings in a variety of contexts. All human facial expressions, whether voluntary or involuntary, are formed as a result of movement of different facial muscles. Despite their variety and complexity, certain expressions are universally recognized as representing specific emotions - for instance, raised eyebrows in combination with an open mouth are associated with surprise, whereas a smiling face is generally interpreted as happy. Deep learning-based implementations of expression synthesis have demonstrated their ability to preserve essential features of input images, which is desirable. However, one limitation of using deep learning networks is that their dependence on data distribution and the quality of images used for training purposes. The variation in performance can be studied by changing the optimizer and loss functions, and their effectiveness is analysed based on the quality of output images obtained.

scholarly journals Deep learning for semantic segmentation of organs and tissues in laparoscopic surgery

2020 ◽  
Vol 6 (1) ◽  
Author(s):  
Paul Maria Scheikl ◽  
Stefan Laschewski ◽  
Anna Kisilenko ◽  
Tornike Davitashvili ◽  
Benjamin Müller ◽  
...  
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Laparoscopic Surgery ◽  
Semantic Segmentation ◽  
Cognitive Robotics ◽  
Loss Functions ◽  
Cognitive Systems ◽  
Context Aware ◽  
Segmentation Quality ◽  
And Training

AbstractSemantic segmentation of organs and tissue types is an important sub-problem in image based scene understanding for laparoscopic surgery and is a prerequisite for context-aware assistance and cognitive robotics. Deep Learning (DL) approaches are prominently applied to segmentation and tracking of laparoscopic instruments. This work compares different combinations of neural networks, loss functions, and training strategies in their application to semantic segmentation of different organs and tissue types in human laparoscopic images in order to investigate their applicability as components in cognitive systems. TernausNet-11 trained on Soft-Jaccard loss with a pretrained, trainable encoder performs best in regard to segmentation quality (78.31% mean Intersection over Union [IoU]) and inference time (28.07 ms) on a single GTX 1070 GPU.

Sign in / Sign up

Export Citation Format

Share Document