scholarly journals Topological Uncertainty: Monitoring Trained Neural Networks through Persistence of Activation Graphs

2021 ◽  
Author(s):  
Théo Lacombe ◽  
Yuichi Ike ◽  
Mathieu Carrière ◽  
Frédéric Chazal ◽  
Marc Glisse ◽  
...  
Keyword(s):  
Neural Networks ◽  
Network Architecture ◽  
Data Augmentation ◽  
Industrial Applications ◽  
Data Types ◽  
Open World ◽  
Use Of Data ◽  
Uncertainty Monitoring ◽  
Final Layer ◽  
Benchmark Datasets

Although neural networks are capable of reaching astonishing performance on a wide variety of contexts, properly training networks on complicated tasks requires expertise and can be expensive from a computational perspective. In industrial applications, data coming from an open-world setting might widely differ from the benchmark datasets on which a network was trained. Being able to monitor the presence of such variations without retraining the network is of crucial importance. In this paper, we develop a method to monitor trained neural networks based on the topological properties of their activation graphs. To each new observation, we assign a Topological Uncertainty, a score that aims to assess the reliability of the predictions by investigating the whole network instead of its final layer only as typically done by practitioners. Our approach entirely works at a post-training level and does not require any assumption on the network architecture, optimization scheme, nor the use of data augmentation or auxiliary datasets; and can be faithfully applied on a large range of network architectures and data types. We showcase experimentally the potential of Topological Uncertainty in the context of trained network selection, Out-Of-Distribution detection, and shift-detection, both on synthetic and real datasets of images and graphs.

scholarly journals X-ray image based pneumonia classification using convolutional neural networks

2020 ◽  
Vol 6 (20) ◽  
pp. 54-67
Author(s):  
Sarah Badr AlSumairi ◽  
Mohamed Maher Ben Ismail
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Network Architecture ◽  
Data Augmentation ◽  
Critical Factor ◽  
Classification Problem ◽  
X Rays ◽  
X Ray ◽  
Erroneous Decision ◽  
Short Period

Pneumonia is an infectious disease of the lungs. About one third to one half of pneumonia cases are caused by bacteria. Early diagnosis is a critical factor for a successful treatment process. Typically, the disease can be diagnosed by a radiologist using chest X-ray images. In fact, chest X-rays are currently the best available method for diagnosing pneumonia. However, the recognition of pneumonia symptoms is a challenging task that relies on the availability of expert radiologists. Such “human” diagnosis can be inaccurate and subjective due to lack of clarity and erroneous decision. Moreover, the error can increase more if the physician is requested to analyze tens of X-rays within a short period of time. Therefore, Computer-Aided Diagnosis (CAD) systems were introduced to support and assist physicians and make their efforts more productive. In this paper, we investigate, design, implement and assess customized Convolutional Neural Networks to overcome the image-based Pneumonia classification problem. Namely, ResNet-50 and DenseNet-161 models were inherited to design customized deep network architecture and improve the overall pneumonia classification accuracy. Moreover, data augmentation was deployed and associated with standard datasets to assess the proposed models. Besides, standard performance measures were used to validate and evaluate the proposed system.

scholarly journals Understanding unconventional preprocessors in deep convolutional neural networks for face identification

2019 ◽  
Vol 1 (11) ◽  
Author(s):  
Chollette C. Olisah ◽  
Lyndon Smith
Keyword(s):  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Network Architecture ◽  
Data Augmentation ◽  
Color Space ◽  
Back Propagation ◽  
Face Identification ◽  
Deep Convolutional Neural Networks ◽  
Softmax Classifier ◽  
Deep Network

Abstract Deep convolutional neural networks have achieved huge successes in application domains like object and face recognition. The performance gain is attributed to different facets of the network architecture such as: depth of the convolutional layers, activation function, pooling, batch normalization, forward and back propagation and many more. However, very little emphasis is made on the preprocessor’s module of the network. Therefore, in this paper, the network’s preprocessing module is varied across different preprocessing approaches while keeping constant other facets of the deep network architecture, to investigate the contribution preprocessing makes to the network. Commonly used preprocessors are the data augmentation and normalization and are termed conventional preprocessors. Others are termed the unconventional preprocessors, they are: color space converters; grey-level resolution preprocessors; full-based and plane-based image quantization, Gaussian blur, illumination normalization and insensitive feature preprocessors. To achieve fixed network parameters, CNNs with transfer learning is employed. The aim is to transfer knowledge from the high-level feature vectors of the Inception-V3 network to offline preprocessed LFW target data; and features is trained using the SoftMax classifier for face identification. The experiments show that the discriminative capability of the deep networks can be improved by preprocessing RGB data with some of the unconventional preprocessors before feeding it to the CNNs. However, for best performance, the right setup of preprocessed data with augmentation and/or normalization is required. Summarily, preprocessing data before it is fed to the deep network is found to increase the homogeneity of neighborhood pixels even at reduced bit depth which serves for better storage efficiency.

scholarly journals Sharing Residual Units Through Collective Tensor Factorization To Improve Deep Neural Networks

2018 ◽  
Author(s):  
Yunpeng Chen ◽  
Xiaojie Jin ◽  
Bingyi Kang ◽  
Jiashi Feng ◽  
Shuicheng Yan
Keyword(s):  
Neural Networks ◽  
Network Architecture ◽  
Deep Neural Networks ◽  
Tensor Decomposition ◽  
Classification Performance ◽  
Model Parameters ◽  
Tensor Factorization ◽  
Unified Framework ◽  
Benchmark Datasets ◽  
Basic Network

The residual unit and its variations are wildly used in building very deep neural networks for alleviating optimization difficulty. In this work, we revisit the standard residual function as well as its several successful variants and propose a unified framework based on tensor Block Term Decomposition (BTD) to explain these apparently different residual functions from the tensor decomposition view. With the BTD framework, we further propose a novel basic network architecture, named the Collective Residual Unit (CRU). CRU further enhances parameter efficiency of deep residual neural networks by sharing core factors derived from collective tensor factorization over the involved residual units. It enables efficient knowledge sharing across multiple residual units, reduces the number of model parameters, lowers the risk of over-fitting, and provides better generalization ability. Extensive experimental results show that our proposed CRU network brings outstanding parameter efficiency -- it achieves comparable classification performance with ResNet-200 while using a model size as small as ResNet-50 on the ImageNet-1k and Places365-Standard benchmark datasets.

scholarly journals A comprehensive study on classification of COVID-19 on computed tomography with pretrained convolutional neural networks

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Tuan D. Pham
Keyword(s):  
Computed Tomography ◽  
Neural Networks ◽  
Convolutional Neural Networks ◽  
High Performance ◽  
Data Augmentation ◽  
Ct Scans ◽  
Automated Classification ◽  
Imaging Data ◽  
Use Of Data

Abstract The use of imaging data has been reported to be useful for rapid diagnosis of COVID-19. Although computed tomography (CT) scans show a variety of signs caused by the viral infection, given a large amount of images, these visual features are difficult and can take a long time to be recognized by radiologists. Artificial intelligence methods for automated classification of COVID-19 on CT scans have been found to be very promising. However, current investigation of pretrained convolutional neural networks (CNNs) for COVID-19 diagnosis using CT data is limited. This study presents an investigation on 16 pretrained CNNs for classification of COVID-19 using a large public database of CT scans collected from COVID-19 patients and non-COVID-19 subjects. The results show that, using only 6 epochs for training, the CNNs achieved very high performance on the classification task. Among the 16 CNNs, DenseNet-201, which is the deepest net, is the best in terms of accuracy, balance between sensitivity and specificity, $$F_1$$ F 1 score, and area under curve. Furthermore, the implementation of transfer learning with the direct input of whole image slices and without the use of data augmentation provided better classification rates than the use of data augmentation. Such a finding alleviates the task of data augmentation and manual extraction of regions of interest on CT images, which are adopted by current implementation of deep-learning models for COVID-19 classification.

scholarly journals Selection of neural network architecture and data augmentation procedures for predicting the course of cardiovascular diseases

2021 ◽  
Vol 2094 (3) ◽  
pp. 032037
Author(s):  
M G Dorrer ◽  
S E Golovenkin ◽  
S Yu Nikulina ◽  
Yu V Orlova ◽  
E Yu Pelipeckaya ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Cardiovascular Diseases ◽  
Network Architecture ◽  
Data Augmentation ◽  
Case Histories ◽  
Neural Network Architecture ◽  
Original Dataset ◽  
Augmentation Procedure ◽  
Selection Of

Abstract The article solves the problem of creating models for predicting the course and complications of cardiovascular diseases. Artificial neural networks based on the Keras library are used. The original dataset includes 1700 case histories. In addition, the dataset augmentation procedure was used. As a result, the overall accuracy exceeded 84%. Furthermore, optimizing the network architecture and dataset has increased the overall accuracy by 17% and precision by 7%.

scholarly journals Novel convolutional neural networks for efficient classification of rotated and scaled images

2021 ◽  
Author(s):  
Paweł Tarasiuk ◽  
Piotr S. Szczepaniak
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Network Architecture ◽  
Data Augmentation ◽  
Network Models ◽  
Input Image ◽  
Feature Maps ◽  
Neural Network Models ◽  
Geometric Transformations

AbstractThis paper presents a novel method for improving the invariance of convolutional neural networks (CNNs) to selected geometric transformations in order to obtain more efficient image classifiers. A common strategy employed to achieve this aim is to train the network using data augmentation. Such a method alone, however, increases the complexity of the neural network model, as any change in the rotation or size of the input image results in the activation of different CNN feature maps. This problem can be resolved by the proposed novel convolutional neural network models with geometric transformations embedded into the network architecture. The evaluation of the proposed CNN model is performed on the image classification task with the use of diverse representative data sets. The CNN models with embedded geometric transformations are compared to those without the transformations, using different data augmentation setups. As the compared approaches use the same amount of memory to store the parameters, the improved classification score means that the proposed architecture is more optimal.

Early and Late Level Fusion of Deep Convolutional Neural Networks for Visual Concept Recognition

2016 ◽  
Vol 10 (03) ◽  
pp. 379-397 ◽  
Author(s):  
Hilal Ergun ◽  
Yusuf Caglar Akyuz ◽  
Mustafa Sert ◽  
Jianquan Liu
Keyword(s):  
Neural Networks ◽  
Best Practices ◽  
Convolutional Neural Networks ◽  
Network Architecture ◽  
Data Augmentation ◽  
State Of The Art ◽  
Great Promise ◽  
Visual Concept ◽  
Deep Convolutional Neural Networks ◽  
Concept Recognition

Visual concept recognition is an active research field in the last decade. Related to this attention, deep learning architectures are showing great promise in various computer vision domains including image classification, object detection, event detection and action recognition in videos. In this study, we investigate various aspects of convolutional neural networks for visual concept recognition. We analyze recent studies and different network architectures both in terms of running time and accuracy. In our proposed visual concept recognition system, we first discuss various important properties of popular convolutional network architecture under consideration. Then we describe our method for feature extraction at different levels of abstraction. We present extensive empirical information along with best practices for big data practitioners. Using these best practices we propose efficient fusion mechanisms both for single and multiple network models. We present state-of-the-art results on benchmark datasets while keeping computational costs at low level. Our results show that these state-of-the-art results can be reached without using extensive data augmentation techniques.

Deep Learning Classification on Optical Coherence Tomography Retina Images

2019 ◽  
Vol 34 (08) ◽  
pp. 2052002
Author(s):  
Frank Y. Shih ◽  
Himanshu Patel
Keyword(s):  
Neural Networks ◽  
Optical Coherence Tomography ◽  
Deep Learning ◽  
Network Architecture ◽  
Data Augmentation ◽  
Training Data ◽  
Retinal Images ◽  
Optical Coherence ◽  
Rgb Images ◽  
Testing Accuracy

This paper presents a novel deep learning classification technique applied on optical coherence tomography (OCT) retinal images. We propose the deep neural networks based on Vgg16 pre-trained network model. The OCT retinal image dataset consists of four classes, including three most common retina diseases and one normal retina scan. Because the scale of training data is not sufficiently large, we use the transfer learning technique. Since the convolutional neural networks are sensitive to a little data change, we use data augmentation to analyze the classified results on retinal images. The input grayscale OCT scan images are converted to RGB images using colormaps. We have evaluated different types of classifiers with variant parameters in training the network architecture. Experimental results show that testing accuracy of 99.48% can be obtained as combined on all the classes.

scholarly journals Hierarchical Convolutional Neural Network for Infrared Image Super-Resolution

2021 ◽  
Vol 26 (1) ◽  
Author(s):  
Maksym Oleksandrovych Yaroshenko ◽  
Anton Yuriiovych Varfolomieiev ◽  
Petro Oleksiyovych Yaganov
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Architecture ◽  
Data Augmentation ◽  
Super Resolution ◽  
Learning Rate ◽  
High Price ◽  
Training Procedure ◽  
High Quality

Due to the high price of thermal imaging sensors, methods for high quality upscaling of infrared images, acquired from low-resolution inexpensive IR-cameras become in high demand. One of the very promising branches of such kinds of methods is base on super-resolution (SR) techniques that exploit convolutional neural networks (CNN), which are developed rapidly for the last decade. During the review of existing solutions, we found that most of the super-resolution neural networks are intended for the upscaling of images in the visible spectrum band. Among them, the BCLSR network has proven to be one of the best solutions that ensure a very high quality of image upscaling. Thus, we selected this network for further investigation in the current paper. Namely, in this research, we trained and tested the BCLSR network for upscaling of far-infrared (FIR) images for the first time. Moreover, inspired by the BCLSR architecture, we proposed our own neural network, which defers from the BCLSR by the absence of recursive and recurrent layers that were replaced by series-connected Residual- and parallel-connected Inception-like blocks correspondingly. During the tests, we found that the suggested modifications permit to increase the network inference speed almost twice and even improve the quality of upscaling by 0,063 dB compared to the basic BCLSR implementation. Networks were trained and tested using the CVC-14 dataset that contains FIR images acquired at the night. We used data augmentation with random dividing dataset images onto 100×100 pixel patches and with subsequent application random brightness, contrast, and mirroring to the obtained patches. The training procedure was performed in a single cycle with single increase and decrease of the learning rate and used the same parameters for the proposed and the BCLSR networks. We employed the Adam optimizer for the training of both networks. Nevertheless, the proposed model has more parameters (2,7 М) compared to the BCLSR (0,6 М), both of the networks can be considered as the small ones, and thus can be used in applications for conventional personal computers, as well as in embedded solutions. The direction of the further research can be focused on the improvements of the proposed network architecture by introducing new types of layers as well as on the modifying of hyperparameters of the used layers. The quality of the upscaling can be increased also by using other loss functions and by the change of learning rate-varying strategies.

scholarly journals Memory Attention Networks for Skeleton-based Action Recognition

2018 ◽  
Author(s):  
Chunyu Xie ◽  
Ce Li ◽  
Baochang Zhang ◽  
Chen Chen ◽  
Jungong Han ◽  
...  
Keyword(s):  
Neural Networks ◽  
Action Recognition ◽  
Network Architecture ◽  
Recognition Task ◽  
Temporal Variations ◽  
Temporal Attention ◽  
Attention Networks ◽  
Benchmark Datasets ◽  
End To End ◽  
Spatio Temporal

Skeleton-based action recognition task is entangled with complex spatio-temporal variations of skeleton joints, and remains challenging for Recurrent Neural Networks (RNNs). In this work, we propose a temporal-then-spatial recalibration scheme to alleviate such complex variations, resulting in an end-to-end Memory Attention Networks (MANs) which consist of a Temporal Attention Recalibration Module (TARM) and a Spatio-Temporal Convolution Module (STCM). Specifically, the TARM is deployed in a residual learning module that employs a novel attention learning network to recalibrate the temporal attention of frames in a skeleton sequence. The STCM treats the attention calibrated skeleton joint sequences as images and leverages the Convolution Neural Networks (CNNs) to further model the spatial and temporal information of skeleton data. These two modules (TARM and STCM) seamlessly form a single network architecture that can be trained in an end-to-end fashion. MANs significantly boost the performance of skeleton-based action recognition and achieve the best results on four challenging benchmark datasets: NTU RGB+D, HDM05, SYSU-3D and UT-Kinect.

Sign in / Sign up

Export Citation Format

Share Document