scholarly journals A Transfer Learning Evaluation of Deep Neural Networks for Image Classification

2022 ◽  
Vol 4 (1) ◽  
pp. 22-41
Author(s):  
Nermeen Abou Baker ◽  
Nico Zengeler ◽  
Uwe Handmann
Keyword(s):  
Image Classification ◽  
Transfer Learning ◽  
High Performance ◽  
Target Domain ◽  
Training Time ◽  
Learning Evaluation ◽  
Learning Technique ◽  
General Network ◽  
Model Size ◽  
Classification Tasks

Transfer learning is a machine learning technique that uses previously acquired knowledge from a source domain to enhance learning in a target domain by reusing learned weights. This technique is ubiquitous because of its great advantages in achieving high performance while saving training time, memory, and effort in network design. In this paper, we investigate how to select the best pre-trained model that meets the target domain requirements for image classification tasks. In our study, we refined the output layers and general network parameters to apply the knowledge of eleven image processing models, pre-trained on ImageNet, to five different target domain datasets. We measured the accuracy, accuracy density, training time, and model size to evaluate the pre-trained models both in training sessions in one episode and with ten episodes.

Cross-domain gearbox diagnostics under variable working conditions with deep convolutional transfer learning

2020 ◽  
pp. 107754632093379
Author(s):  
Moslem Azamfar ◽  
Jaskaran Singh ◽  
Xiang Li ◽  
Jay Lee
Keyword(s):  
Fault Diagnosis ◽  
Transfer Learning ◽  
High Performance ◽  
Training Sample ◽  
Training Dataset ◽  
Target Domain ◽  
Training Sample Size ◽  
Vibration Data ◽  
Cross Domain ◽  
Testing Dataset

This study proposes a novel 1D deep convolutional transfer learning method that is able to learn the high-dimensional domain-invariant feature from the labeled training dataset and perform diagnosis tasks on the unlabeled testing dataset subjected to a domain shift. To obtain the domain-invariant features, the cross-entropy loss in the source domain classifier and the maximum mean discrepancies between the source and target domain data are minimized simultaneously. To evaluate the performance of the proposed method, an experimental study is conducted on a gearbox under significant speed variation. Because of inherent limitations of the vibration data, in this research, the effectiveness of torque measurement signals has been explored for gearbox fault diagnosis. Comprehensive studies on network parameters and the training sample size are performed to illustrate the robustness and effectiveness of the proposed method. A comparison study is performed on similar techniques to illustrate the superiority and high performance of the proposed diagnosis method. The achieved results illustrate the effectiveness of torque signal in multiclass cross-domain fault diagnosis of gearboxes.

scholarly journals Transfer learning for hostel image classification

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Chanattra Ammatmanee ◽  
Lu Gan
Keyword(s):  
Image Classification ◽  
Transfer Learning ◽  
Data Augmentation ◽  
Image Database ◽  
Learning Ability ◽  
Learning Technology ◽  
Human Errors ◽  
Content Type ◽  
Training Time ◽  
Processing Steps

PurposeBecause of the fast-growing digital image collections on online platforms and the transfer learning ability of deep learning technology, image classification could be improved and implemented for the hostel domain, which has complex clusters of image contents. This paper aims to test the potential of 11 pretrained convolutional neural network (CNN) with transfer learning for hostel image classification on the first hostel image database to advance the knowledge and fill the gap academically, as well as to suggest an alternative solution in optimal image classification with less labour cost and human errors to those who manage hostel image collections.Design/methodology/approachThe hostel image database is first created with data pre-processing steps, data selection and data augmentation. Then, the systematic and comprehensive investigation is divided into seven experiments to test 11 pretrained CNNs which transfer learning was applied and parameters were fine-tuned to match this newly created hostel image dataset. All experiments were conducted in Google Colaboratory environment using PyTorch.FindingsThe 7,350 hostel image database is created and labelled into seven classes. Furthermore, its experiment results highlight that DenseNet 121 and DenseNet 201 have the greatest potential for hostel image classification as they outperform other CNNs in terms of accuracy and training time.Originality/valueThe fact that there is no existing academic work dedicating to test pretrained CNNs with transfer learning for hostel image classification and no existing hostel image-only database have made this paper a novel contribution.

scholarly journals Is One Teacher Model Enough to Transfer Knowledge to a Student Model?

Algorithms ◽  
2021 ◽  
Vol 14 (11) ◽  
pp. 334
Author(s):  
Nicola Landro ◽  
Ignazio Gallo ◽  
Riccardo La Grassa
Keyword(s):  
Neural Network ◽  
Transfer Learning ◽  
Learning Problem ◽  
Learning Techniques ◽  
Starting Point ◽  
Learning Technique ◽  
Interesting Approach ◽  
Classification Tasks ◽  
Learned Features ◽  
Fine Tune

Nowadays, the transfer learning technique can be successfully applied in the deep learning field through techniques that fine-tune the CNN’s starting point so it may learn over a huge dataset such as ImageNet and continue to learn on a fixed dataset to achieve better performance. In this paper, we designed a transfer learning methodology that combines the learned features of different teachers to a student network in an end-to-end model, improving the performance of the student network in classification tasks over different datasets. In addition to this, we tried to answer the following questions which are in any case directly related to the transfer learning problem addressed here. Is it possible to improve the performance of a small neural network by using the knowledge gained from a more powerful neural network? Can a deep neural network outperform the teacher using transfer learning? Experimental results suggest that neural networks can transfer their learning to student networks using our proposed architecture, designed to bring to light a new interesting approach for transfer learning techniques. Finally, we provide details of the code and the experimental settings.

scholarly journals Convolutional neural network for image classification based on transfer learning technique

2021 ◽  
Author(s):  
Ghassan Mohammed Halawani
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Image Classification ◽  
Transfer Learning ◽  
Learning Networks ◽  
The Neural Network ◽  
Learning Technique ◽  
Common Architecture

The main purpose of this project is to modify a convolutional neural network for image classification, based on a deep-learning framework. A transfer learning technique is used by the MATLAB interface to Alex-Net to train and modify the parameters in the last two fully connected layers of Alex-Net with a new dataset to perform classifications of thousands of images. First, the general common architecture of most neural networks and their benefits are presented. The mathematical models and the role of each part in the neural network are explained in detail. Second, different neural networks are studied in terms of architecture, application, and the working method to highlight the strengths and weaknesses of each of neural network. The final part conducts a detailed study on one of the most powerful deep-learning networks in image classification – i.e. the convolutional neural network – and how it can be modified to suit different classification tasks by using transfer learning technique in MATLAB.

scholarly journals A novel augmented deep transfer learning for classification of COVID-19 and other thoracic diseases from X-rays

2021 ◽  
Author(s):  
Fouzia Altaf ◽  
Syed M. S. Islam ◽  
Naeem Khalid Janjua
Keyword(s):  
Deep Learning ◽  
Medical Imaging ◽  
Transfer Learning ◽  
Medical Images ◽  
Training Data ◽  
Target Domain ◽  
Data Set ◽  
Learning Technique ◽  
Multi Class Classification ◽  
Effective Transfer

AbstractDeep learning has provided numerous breakthroughs in natural imaging tasks. However, its successful application to medical images is severely handicapped with the limited amount of annotated training data. Transfer learning is commonly adopted for the medical imaging tasks. However, a large covariant shift between the source domain of natural images and target domain of medical images results in poor transfer learning. Moreover, scarcity of annotated data for the medical imaging tasks causes further problems for effective transfer learning. To address these problems, we develop an augmented ensemble transfer learning technique that leads to significant performance gain over the conventional transfer learning. Our technique uses an ensemble of deep learning models, where the architecture of each network is modified with extra layers to account for dimensionality change between the images of source and target data domains. Moreover, the model is hierarchically tuned to the target domain with augmented training data. Along with the network ensemble, we also utilize an ensemble of dictionaries that are based on features extracted from the augmented models. The dictionary ensemble provides an additional performance boost to our method. We first establish the effectiveness of our technique with the challenging ChestXray-14 radiography data set. Our experimental results show more than 50% reduction in the error rate with our method as compared to the baseline transfer learning technique. We then apply our technique to a recent COVID-19 data set for binary and multi-class classification tasks. Our technique achieves 99.49% accuracy for the binary classification, and 99.24% for multi-class classification.

scholarly journals Automated Machine Learning for High-Throughput Image-Based Plant Phenotyping

2021 ◽  
Vol 13 (5) ◽  
pp. 858
Author(s):  
Joshua C.O. Koh ◽  
German Spangenberg ◽  
Surya Kant
Keyword(s):  
Machine Learning ◽  
Image Classification ◽  
Transfer Learning ◽  
Precision Agriculture ◽  
High Performance ◽  
Mean Squared Error ◽  
Plant Phenotyping ◽  
Percentage Error ◽  
Great Promise ◽  
Automated Machine Learning

Automated machine learning (AutoML) has been heralded as the next wave in artificial intelligence with its promise to deliver high-performance end-to-end machine learning pipelines with minimal effort from the user. However, despite AutoML showing great promise for computer vision tasks, to the best of our knowledge, no study has used AutoML for image-based plant phenotyping. To address this gap in knowledge, we examined the application of AutoML for image-based plant phenotyping using wheat lodging assessment with unmanned aerial vehicle (UAV) imagery as an example. The performance of an open-source AutoML framework, AutoKeras, in image classification and regression tasks was compared to transfer learning using modern convolutional neural network (CNN) architectures. For image classification, which classified plot images as lodged or non-lodged, transfer learning with Xception and DenseNet-201 achieved the best classification accuracy of 93.2%, whereas AutoKeras had a 92.4% accuracy. For image regression, which predicted lodging scores from plot images, transfer learning with DenseNet-201 had the best performance (R2 = 0.8303, root mean-squared error (RMSE) = 9.55, mean absolute error (MAE) = 7.03, mean absolute percentage error (MAPE) = 12.54%), followed closely by AutoKeras (R2 = 0.8273, RMSE = 10.65, MAE = 8.24, MAPE = 13.87%). In both tasks, AutoKeras models had up to 40-fold faster inference times compared to the pretrained CNNs. AutoML has significant potential to enhance plant phenotyping capabilities applicable in crop breeding and precision agriculture.

scholarly journals Image Classification using ImageNet Classifiers in Environments with Limited Data

2021 ◽  
Author(s):  
Anirvin Sharma ◽  
Abhinav Singh ◽  
Tanupriya Choudhury ◽  
Tanmay Sarkar
Keyword(s):  
Image Classification ◽  
Transfer Learning ◽  
Data Augmentation ◽  
Classification Algorithms ◽  
Limited Data ◽  
Training Time ◽  
Learning Framework ◽  
Rare Phenomena ◽  
Fully Connected ◽  
Compare And Contrast

Abstract In this research, we compare and contrast various image classification algorithms and how effective they are in specific problem sets where data might be scarce such as prediction of rare phenomena (for example, natural calamities), enterprise solutions etc. We have employed various state-of-the-art algorithms in this study credited to have been some of the best classifiers at the time of their inception. These classifiers have also been suspected to fall prey to overfitting on the datasets they were initially tested on viz. ImageNet and Common Objects in Context (COCO); we test to what extent these classifiers tend to generalize to the new data provided by us in a transfer learning framework. We utilize transfer learning on the ImageNet classifiers to adapt to our smaller dataset and examine various techniques such as data augmentation, batch normalization, dropout etc. to mitigate overfitting. All the classifiers follow a standard fully connected architecture. The end result should provide the reader with an overall analysis of which algorithm or approach to use in conditions where data might be limited while also giving a brief overview of the progress of image classification algorithms since their advent. We also provide an analysis on the effectiveness of data augmentation in limited datasets by providing results achieved with and without utilizing data augmentation. In our case, we found the MobileNet (with its lightweight nature contributing to low computational costs) and InceptionV3 (owing to its lower training time) to be the best performing classifiers for applying transfer learning to limited datasets out of the classifiers we have used for our study. This paper aims to establish preemptive standards that can be used to evaluate the models which can be used in object recognition, and image classification for problems containing limited amounts of data.

scholarly journals Cross-Domain Reuse of Extracted Knowledge in Genetic Programming for Image Classification

2020 ◽  
Author(s):  
M Iqbal ◽  
Bing Xue ◽  
Harith Al-Sahaf ◽  
Mengjie Zhang
Keyword(s):  
Genetic Programming ◽  
Image Classification ◽  
Transfer Learning ◽  
Evolutionary Process ◽  
Classification Performance ◽  
Data Sets ◽  
Classification Problems ◽  
Novel Approach ◽  
Complex Image ◽  
Classification Tasks

© 2017 IEEE. Genetic programming (GP) is a well-known evolutionary computation technique, which has been successfully used to solve various problems, such as optimization, image analysis, and classification. Transfer learning is a type of machine learning approach that can be used to solve complex tasks. Transfer learning has been introduced to GP to solve complex Boolean and symbolic regression problems with some promise. However, the use of transfer learning with GP has not been investigated to address complex image classification tasks with noise and rotations, where GP cannot achieve satisfactory performance, but GP with transfer learning may improve the performance. In this paper, we propose a novel approach based on transfer learning and GP to solve complex image classification problems by extracting and reusing blocks of knowledge/information, which are automatically discovered from similar as well as different image classification tasks during the evolutionary process. The proposed approach is evaluated on three texture data sets and three office data sets of image classification benchmarks, and achieves better classification performance than the state-of-the-art image classification algorithm. Further analysis on the evolved solutions/trees shows that the proposed approach with transfer learning can successfully discover and reuse knowledge/information extracted from similar or different problems to improve its performance on complex image classification problems.

scholarly journals Deep Transfer Learning for Biology Cross-Domain Image Classification

2021 ◽  
Vol 2021 ◽  
pp. 1-19
Author(s):  
Chunfeng Guo ◽  
Bin Wei ◽  
Kun Yu
Keyword(s):  
Image Classification ◽  
Transfer Learning ◽  
Poor Performance ◽  
Target Domain ◽  
Deep Convolutional Neural Networks ◽  
Specific Domain ◽  
Source Domain ◽  
Cross Domain ◽  
Domain Transfer ◽  
Domain Transfer Learning

Automatic biology image classification is essential for biodiversity conservation and ecological study. Recently, due to the record-shattering performance, deep convolutional neural networks (DCNNs) have been used more often in biology image classification. However, training DCNNs requires a large amount of labeled data, which may be difficult to collect for some organisms. This study was carried out to exploit cross-domain transfer learning for DCNNs with limited data. According to the literature, previous studies mainly focus on transferring from ImageNet to a specific domain or transferring between two closely related domains. While this study explores deep transfer learning between species from different domains and analyzes the situation when there is a huge difference between the source domain and the target domain. Inspired by the analysis of previous studies, the effect of biology cross-domain image classification in transfer learning is proposed. In this work, the multiple transfer learning scheme is designed to exploit deep transfer learning on several biology image datasets from different domains. There may be a huge difference between the source domain and the target domain, causing poor performance on transfer learning. To address this problem, multistage transfer learning is proposed by introducing an intermediate domain. The experimental results show the effectiveness of cross-domain transfer learning and the importance of data amount and validate the potential of multistage transfer learning.

Cross-Modality Transfer Learning for Image-Text Information Management

2022 ◽  
Vol 13 (1) ◽  
pp. 1-14
Author(s):  
Shuteng Niu ◽  
Yushan Jiang ◽  
Bowen Chen ◽  
Jian Wang ◽  
Yongxin Liu ◽  
...  
Keyword(s):  
Image Classification ◽  
Information Management ◽  
Transfer Learning ◽  
Information Transfer ◽  
Image Data ◽  
Machine Learning Algorithms ◽  
Training Data ◽  
Classification Problems ◽  
Target Domain ◽  
Text Data

In the past decades, information from all kinds of data has been on a rapid increase. With state-of-the-art performance, machine learning algorithms have been beneficial for information management. However, insufficient supervised training data is still an adversity in many real-world applications. Therefore, transfer learning (TF) was proposed to address this issue. This article studies a not well investigated but important TL problem termed cross-modality transfer learning (CMTL). This topic is closely related to distant domain transfer learning (DDTL) and negative transfer. In general, conventional TL disciplines assume that the source domain and the target domain are in the same modality. DDTL aims to make efficient transfers even when the domains or the tasks are entirely different. As an extension of DDTL, CMTL aims to make efficient transfers between two different data modalities, such as from image to text. As the main focus of this study, we aim to improve the performance of image classification by transferring knowledge from text data. Previously, a few CMTL algorithms were proposed to deal with image classification problems. However, most existing algorithms are very task specific, and they are unstable on convergence. There are four main contributions in this study. First, we propose a novel heterogeneous CMTL algorithm, which requires only a tiny set of unlabeled target data and labeled source data with associate text tags. Second, we introduce a latent semantic information extraction method to connect the information learned from the image data and the text data. Third, the proposed method can effectively handle the information transfer across different modalities (text-image). Fourth, we examined our algorithm on a public dataset, Office-31. It has achieved up to 5% higher classification accuracy than “non-transfer” algorithms and up to 9% higher than existing CMTL algorithms.

Sign in / Sign up

Export Citation Format

Share Document