Classification of jujube defects in small data sets based on transfer learning

目的 基于计算机的胸腔X线影像疾病检测和分类目前存在误诊率高，准确率低的问题。本文在视觉Transformer（vision Transformer，ViT）预训练模型的基础上，通过迁移学习方法，实现胸腔X线影像辅助诊断，提高诊断准确率和效率。方法 选用带有卷积神经网络（convolutional neural network，CNN）的ViT模型，其在超大规模自然图像数据集中进行了预训练；通过微调模型结构，使用预训练的ViT模型参数初始化主干网络，并迁移至胸腔X线影像数据集中再次训练，实现疾病多标签分类。结果 在IU X-Ray数据集中对ViT迁移学习前、后模型平均AUC（area under ROC curve）得分进行对比分析实验。结果表明，预训练ViT模型平均AUC得分为0.774，与不使用迁移学习相比提升了0.208。并针对模型结构和数据预处理进行了消融实验，对ViT中的注意力机制进行可视化，进一步验证了模型有效性。最后使用Chest X-Ray14和CheXpert数据集训练微调后的ViT模型，平均AUC得分为0.839和0.806，与对比方法相比分别有0.014～0.031的提升。结论 与其他方法相比，ViT模型胸腔X线影像的多标签分类精确度更高，且迁移学习可以在降低训练成本的同时提升ViT模型的分类性能和泛化性。消融实验与模型可视化表明，包含CNN结构的ViT模型能重点关注有意义的区域，高效获取胸腔X线影像的视觉特征。;Objective The chest X-ray-relevant screening and diagnostic method is essential for radiology nowadays. Most of chest X-ray images interpretation is still restricted by clinical experience and challenged for misdiagnose and missed diagnoses. To detect and identify one or more potential diseases in images automatically，it is beneficial for improving diagnostic efficiency and accuracy using computer-based technique. Compared to natural images，multiple lesions are challenged to be detected and distinguished accurately in a single image because abnormal areas have a small proportion and complex representations in chest X-ray images. Current convolutional neural network（CNN）based deep learning models have been widely used in the context of medical imaging. The structure of the CNN convolution kernel has sensitive to local detail information，and it is possible to extract richer image features. However，the convolution kernel cannot be used to get global information，and the features-extracted are restricted of redundant information like its relevance of background， muscles，and bones. The model’s performance in multi-label classification tasks are affected to a certain extent. At present，the vision Transformer（ViT）model has achieved its priorities in computer vision-related tasks. The ViT can be used to capture information simultaneously and effectively for multiple regions of the entire image. However，it is required to use large-scale dataset training to achieve good performance. Due to some factors like patient privacy and manual annotate costs，the size of the chest X-ray image data set has been limited. To reduce the model's dependence on data scale and improve the performance of multi-label classification，we develop the CNN-based ViT pre-training model in terms of the transfer learning method for diagnosis-assisted of chest X-ray image and multi-label classification. Method The CNN-based ViT model is pre-trained on a huge scale ground truth dataset，and it is used to obtain the initial parameters of the model. The model structure is fine-tuned according to the features of chest X-ray dataset. A 1×1 convolution layer is used to convert the chest X-ray images channels between 1 to 3. The number of output nodes of the linear layer in the classifier is balanced from 1 000 to the number of chest X-ray classification labels，and the Sigmoid is used as an activation function. The parameters of the backbone network are initialized in terms of the pre-trained ViT model parameters，and it is trained in the chest X-ray dataset after that to complete multi-label classification. The experiment is configured of Python3. 7 and PyTorch1. 8 to construct the model and RTX3090 GPU for training. Stochastic gradient descent（SGD）optimizer，binary cross-entropy（BCE）loss function，an initial learning rate of 1E-3，the cosine annealing learning rate decay are used. For training，each image is scaled to a size of 512×512 pixels，and a 224×224 pixels area and it is then cropped in random as the model input，and data augmentation is performed randomly by some of the flipping，perspective transformation， shearing，translation，zooming，and changing brightness. For testing，the chest X-ray image is scaled to 256×256 pixels and center crop a 224×224 area to input the trained model. Result The experiment is performed on the IU X-Ray，which is a small-scale chest X-ray dataset. This model is evaluated in quantitative using the average of area under ROC curve （AUC）scores across all classification labels. The results show that the average AUC score of the pre-trained ViT model is 0. 774. The accuracy and training efficiency of the non-pre-trained ViT model is dropped significantly. The average AUC score is reached to 0. 566 only，which is 0. 208 lower. In addition，the attention mechanism heat map is generated based on the ViT model，which can strengthen the interpretability of the model. A series of ablation experiments are carried out for data augmentation，model structure，and batch size design. The fine-tuned ViT model is trained on the Chest-Ray14 and CheXpert dataset as well. The average AUC score is reached to 0. 839 and 0. 806，which is optimized by 0. 014 and 0. 031. Conclusion A pre-trained ViT model is used for the multi-label classification of chest X-ray images via transfer learning. The experimental results illustrate that the ViT has its stronger multi-label classification performance in chest Xray images，and its attention mechanism is beneficial for lesions precision-focused like the interior of the chest cavity and the heart. Transfer learning is potential to improve the classification performance and model generalization of the ViT in small-scale datasets，and the training cost is reduced greatly. Ablation experiments demonstrate that the incorporated model of CNN and Transformer has its priority beyond single-structure model. Data enhancement and the batch size cutting can improve the performance of the model，but smaller scale of batch is still interlinked to longer training span. To improve the model's ability，we predict that future research direction can be focused on the extraction for complex disease and highlevel semantic information，such as their small lesions，disease location，and severity.

Quality assurance of data prior to use in automated pipelines and image analysis would assist in safeguarding against biases and incorrect interpretation of results. Automation of quality assurance steps would further improve robustness and efficiency of these methods, motivating widespread adoption of techniques. Previous work by our group demonstrated the ability of convolutional neural networks (CNN) to efficiently classify head and neck (H&N) computed-tomography (CT) images for the presence of dental artifacts (DA) that obscure visualization of structures and the accuracy of Hounsfield units. In this work we demonstrate the generalizability of our previous methodology by validating CNNs on six external datasets, and the potential benefits of transfer learning with fine-tuning on CNN performance. 2112 H&N CT images from seven institutions were scored as DA positive or negative. 1538 images from a single institution were used to train three CNNs with resampling grid sizes of 643, 1283 and 2563. The remaining six external datasets were used in five-fold cross-validation with a data split of 20% training/fine-tuning and 80% validation. The three pre-trained models were each validated using the five-folds of the six external datasets. The pre-trained models also underwent transfer learning with fine-tuning using the 20% training/fine-tuning data, and validated using the corresponding validation datasets. The highest micro-averaged AUC for our pre-trained models across all external datasets occurred with a resampling grid of 2563 (AUC = 0.91 ± 0.01). Transfer learning with fine-tuning improved generalizability when utilizing a resampling grid of 2563 to a micro-averaged AUC of 0.92 ± 0.01. Despite these promising results, transfer learning did not improve AUC when utilizing small resampling grids or small datasets. Our work demonstrates the potential of our previously developed automated quality assurance methods to generalize to external datasets. Additionally, we showed that transfer learning with fine-tuning using small portions of external datasets can be used to fine-tune models for improved performance when large variations in images are present.

As an important part of emotion research, facial expression recognition is a necessary condition for intelligent interaction between human and machine, which has an important research significance and a potential commercial value. Convolutional neural network (CNN) is an effective method to recognize facial emotions, which can perform feature extraction and classification simultaneously, and can automatically discover multiple levels of representations in data. Due to the fact that there are millions of parameters involved in training the convolutional neural network model, and there is a large demand for marked samples, transfer learning is often used to fine-tune the pre-trained model for a small target sample set. However, there are often some content differences between data sets during deep transfer learning, which will affect the recognition ability of feature extraction. In order to improve the facial expression recognition ability in transfer learning, a hybrid transfer learning model based on an improved convolution restricted boltzmann machine (CRBM) model and a CNN model is proposed in this paper. This method is fused by two learning abilities of these two models. When the pre-trained CNN model is transferred to a small target set, the CRBM is used to replace the full connection layer in the CNN model, and the CRBM layer and the sofmax layer will be retrained on the target set. The added CRBM layer can not only fully connects all feature maps, but can also learn about the unique statistical characteristics about the target set, which eliminates the influence of content differences between data sets, and extracts higher-order statistical features of facial expression images from the target set. The proposed method is evaluated based on four publicly available facial expression databases: JAFFE, FER2013, SFEW and RAF-DB. The new method can achieve better performance than most state-of-the-art methods, and it can effectively prevent the negative influence of transfer learning features between different data sets.

Deep convolutional neural networks with ensemble learning and transfer learning for capacity estimation of lithium-ion batteries

The success of Convolutional Neural Network (CNN) is attributed to their ability to learn rich midlevel image representations as opposed to hand-crafted low-level features used in many natural image classification methods. Learning CNN, however, amounts to estimating millions of parameters and requires a very large number of annotated image samples. In this paper, we explored transfer learning for gastrointestinal bleeding detection on small-size imbalanced endoscopy images, and showed how image representations learned with CNN on large-scale annotated datasets can be efficiently transferred to other tasks with limited amount of training data. We first transferred pre-trained Inception V3 model trained on the ImageNet dataset to compute mid-level image representation, and then fine-tuned the trained model with labeled endoscopy images, and resumed training from already learned weights. Additionally, we introduce both data augmentation and image resampling to increase the size of the training database and the positive sample rate to perform the Transfer Learning. Our results showed that our transfer learning method produces the best performance on AUC (the area under the receiver operating curve), Precision, Recall and Accuracy as compared to both the hand-crafted feature based method and training CNN model from-scratch method.

The leather industry plays a crucial role in the production of high-quality leather products to remain competitive in the market. Due to various reasons such as material handling and turning, leather defects can appear at different stages of the production process. This paper proposed deep learning techniques, specifically transfer learning, deep convolutional neural networks (D-CNN), and ensemble learning for automating leather defect detection and classification. The dataset was taken from the open source Kaggle. The dataset was preprocessed from the beginning. However, we performed Error Level Analysis (ELA) to detect possible changes or fraud in the image. We also used data augmentation techniques (resizing, rescaling, flipping, rotation, zooming, and contrasting) on the dataset to improve the model performance. This study investigated deep learning architectures for automatic leather defect detection, comparing them with seven deep convolutional neural networks (D-CNN) models and transfer learning architectures. Furthermore, we introduce and evaluate two novel ensemble models: MER built on transfer learning architecture (MobileNetV2, EfficientNetB0, and ResNet50) and AZL built on D-CNN architecture (AlexNet, ZfNet, and LeNet). A key contribution of this study is the demonstration of significant performance improvements achieved by strategically integrating squeeze and excitation and label smoothing techniques into transfer learning, D-CNN, and ensemble frameworks. Our proposed MER ensemble method achieves a state-of-the-art of 96.39% for leather defect detection. The proposed model was evaluated using performance metrics including precision, recall, F1-score, AUC, ROC, and Matthews Correlation Coefficient (MCC). Additionally, Grad-CAM was employed for explainable AI to visualize and interpret the model’s decision-making process. Comparative analysis against separate transfer learning and D-CNN models fails to establish the superior performance of our MER ensemble, which highlights the potential to significantly advance automated quality inspection in leather production. This study provides insights into evaluating the best deep learning techniques for leather defect classification, paving the way for more accurate, efficient, and reliable industrial applications. Proposes a robust deep learning-based framework for automated leather defect detection using transfer learning, deep CNNs, and two novel ensemble models (MER and AZL), enhanced with squeeze-and-excitation and label smoothing techniques. Achieves state-of-the-art performance with the proposed MER ensemble model, achieve 96.39% accuracy, and demonstrates superior results across precision, recall, F1-score, AUC–ROC, and MCC. Integrates Error Level Analysis (ELA), extensive data augmentation, and Grad-CAM–based explainable AI to ensure data reliability, improve generalization, and provide transparent visual interpretation of defect regions for industrial quality inspection.

Abstract. In recent years, there has been a significant improvement in the detection, identification and classification of objects and images using Convolutional Neural Networks. To study the potential of the Convolutional Neural Network, in this paper three approaches are investigated to train classifiers based on Convolutional Neural Networks. These approaches allow Convolutional Neural Networks to be trained on datasets containing only a few hundred training samples, which results in a successful classification. Two of these approaches are based on the concept of transfer learning. In the first approach features, created by a pretrained Convolutional Neural Network, are used for a classification using a support vector machine. In the second approach a pretrained Convolutional Neural Network gets fine-tuned on a different data set. The third approach includes the design and training for flat Convolutional Neural Networks from the scratch. The evaluation of the proposed approaches is based on a data set provided by the IEEE Geoscience and Remote Sensing Society (GRSS) which contains RGB and LiDAR data of an urban area. In this work it is shown that these Convolutional Neural Networks lead to classification results with high accuracy both on RGB and LiDAR data. Features which are derived by RGB data transferred into LiDAR data by transfer learning lead to better results in classification in contrast to RGB data. Using a neural network which contains fewer layers than common neural networks leads to the best classification results. In this framework, it can furthermore be shown that the practical application of LiDAR images results in a better data basis for classification of vehicles than the use of RGB images.

Comparative analysis of deep convolution neural network models on small scale datasets

Recognition of emotional states using frequency effective connectivity maps through transfer learning approach from electroencephalogram signals

This paper mainly proposes a hyperspectral image object detection algorithm based on transfer learning for Convolutional Neural Networks(CNN). Hyperspectral image object detection is one of the research hotspots in the field of image processing. With the rise of deep learning, more and more scholars have begun to study the application of deep learning in the field of hyperspectral object detection. However, it costs a lot of time for the models based on deep learning to train networks and adjust parameters. This paper mainly studies the correlation between different data sets. It hopes to find the mapping relationship between different data sets by using transfer learning, so as to avoid the time cost of training network. Finally, the paper tests in the PaviaU and PaviaC datasets, and proves that the transfer algorithm proposed in this paper can make the dataset achieve good detection results after transfer.

EEG based multi-class seizure type classification using convolutional neural network and transfer learning

In recent years, Convolutional Neural Networks (CNN) have revealed noteworthy enactment in classification of image jobs. Because of limited availability of annotated brain tumor MRI data, overfitting and lack of generalization are common challenges faced by traditional CNN models. To deal with these challenges, our studies explore the practice of Pre-Trained model of CNN and Transfer learning practices to expand the correctness of cataloguing the brain tumor through the data of MRI. Our experimental results demonstrate that the incorporation of Pre-Trained model of CNN with Transfer learning significantly improves the rain tumor’s classification accuracy on MRI data compared to traditional CNN models trained from scratch. Moreover, the research outcomes highlight potential of transfer learning as an operative approach for improving generalization capabilities of CNN models in medical imaging tasks with limited annotated data. By incorporating pre-trained CNN replicas and transfer erudition techniques, the objective of this studies aims to elevate brain tumor taxonomy accurateness with the assistance of MRI data.

We developed a computer-aided diagnosis (CADx) method for classification between benign nodule, primary lung cancer, and metastatic lung cancer and evaluated the following: (i) the usefulness of the deep convolutional neural network (DCNN) for CADx of the ternary classification, compared with a conventional method (hand-crafted imaging feature plus machine learning), (ii) the effectiveness of transfer learning, and (iii) the effect of image size as the DCNN input. Among 1240 patients of previously-built database, computed tomography images and clinical information of 1236 patients were included. For the conventional method, CADx was performed by using rotation-invariant uniform-pattern local binary pattern on three orthogonal planes with a support vector machine. For the DCNN method, CADx was evaluated using the VGG-16 convolutional neural network with and without transfer learning, and hyperparameter optimization of the DCNN method was performed by random search. The best averaged validation accuracies of CADx were 55.9%, 68.0%, and 62.4% for the conventional method, the DCNN method with transfer learning, and the DCNN method without transfer learning, respectively. For image size of 56, 112, and 224, the best averaged validation accuracy for the DCNN with transfer learning were 60.7%, 64.7%, and 68.0%, respectively. DCNN was better than the conventional method for CADx, and the accuracy of DCNN improved when using transfer learning. Also, we found that larger image sizes as inputs to DCNN improved the accuracy of lung nodule classification.

The research on crop pest identification technology based on image analysis has important practical significance for effectively controlling the occurrence of crop diseases and insect pests (CDIP), improving crop yield and reducing the pollution of pesticides to the environment. Aiming at the problems existing in crop pest recognition technology and aiming at improving the accuracy and efficiency of crop pest recognition, this study proposes a crop pest image recognition method based on transfer learning and convolution neural network. Firstly, the crop pest image is geometrically operated to expand the crop pest image data set, and then the expanded data set is divided into training set and test set. Then, Alexnet, VGG-16, and ResNet-50 models are pretrained on ImageNet large image data set. Based on the theory of transfer learning, the learned model parameters are transferred to the small sample image data set of crop diseases and insect pests in this paper, so as to train the crop diseases and insect pests recognition model. This method is tested on Image Database for Agricultural Diseases and Pests (IDADP). The experimental results show that the convolution neural network plant leaf image recognition method based on transfer learning has better effect. It can quickly and accurately diagnose crop diseases, reduce the use of pesticides and fertilizers, and improve the yield and quality of crops.

The usage of Artificial intelligence in medical arena has proved to be a game changer in the detection and diagnosis of several medical conditions. In the current digital era, children with stressful medical issues are suffering from Deep Obsessive-Compulsive Disorder (DOCD). This kind of mental stress occurs in children because of the continuous usage of gadgets such as mobile phone, playing games using play stations, watching videos on tablets, etc. In most of the possibilities, single children are the ones affected with several obsessions such as stubborn activities, fighting for selfish priorities and so on. In medical terms, these kinds of complex behavioral changes are identified as DOCD. Genetic behaviors sometimes in a few group of children are also noticed as a modality difference. As symptoms are psychiatric impairment, such a child remains isolated, abnormal silence, being obsessive and repeating irrelevant words, high stress or anxiety. All medical challenges could be treated as healthcare research metrics and the gradual increase in DOCD disorder among children of this generation can be considered too. Early detection of DOCD is essential as it can help in early diagnosis but techniques to do so is unavailable currently. Deep learning-an artificial intelligence method can be utilized to detect DOCD, diagnose and treat it and bring about a positive character in children. Behavior changes in children can be classified and detected using transfer learning algorithms. In COVID-19 pandemic situation, 3% of DOCD has increased to 10-15% as a disorder. This information is retrieved from children by monitoring negative activities, unusual behavior such as nail biting, removing spectacles and placing them in the wrong place, watching tablets, mobile phones and television for more hours. Using Convolutional Neural Networks (CNN), input such as MRI (Magnetic resonance Imaging) is used for experimenting the variations in behavior with the high dimension that are analyzed from the image dataset. Using Transfer Learning with Inception V3-, CNN generalization of misophonia level can be statistically analyzed to avoid overfitting problems. By employing AI techniques, the aggression level can be predicted using data augmentation method with better accuracy and a low error rate than the existing systems. In the research it is observed that using the model employing Inception-V3 transfer learning CNN a better prediction of aggression levels can be achieved in comparison to the existing CNN model used.