Metric Embedding Autoencoders for Unsupervised Cross-Dataset Transfer Learning

Skin lesion classification plays a crucial role in dermatology, aiding in the early detection, diagnosis, and management of life-threatening malignant lesions. However, standalone transfer learning (TL) models failed to deliver optimal performance. In this study, we present an attention-enabled ensemble-based deep learning technique, a powerful, novel, and generalized method for extracting features for the classification of skin lesions. This technique holds significant promise in enhancing diagnostic accuracy by using seven pre-trained TL models for classification. Six ensemble-based DL (EBDL) models were created using stacking, softmax voting, and weighted average techniques. Furthermore, we investigated the attention mechanism as an effective paradigm and created seven attention-enabled transfer learning (aeTL) models before branching out to construct three attention-enabled ensemble-based DL (aeEBDL) models to create a reliable, adaptive, and generalized paradigm. The mean accuracy of the TL models is 95.30%, and the use of an ensemble-based paradigm increased it by 4.22%, to 99.52%. The aeTL models’ performance was superior to the TL models in accuracy by 3.01%, and aeEBDL models outperformed aeTL models by 1.29%. Statistical tests show significant p-value and Kappa coefficient along with a 99.6% reliability index for the aeEBDL models. The approach is highly effective and generalized for the classification of skin lesions.

Most existing person re-identification(Re-ID) approaches achieve superior results based on the assumption that a large amount of pre-labelled data is usually available and can be put into training phrase all at once. However, this assumption is not applicable to most real-world deployment of the Re-ID task. In this work, we propose an alternative reinforcement learning based human-in-the-loop model which releases the restriction of pre-labelling and keeps model upgrading with progressively collected data. The goal is to minimize human annotation efforts while maximizing Re-ID performance. It works in an iteratively updating framework by refining the RL policy and CNN parameters alternately. In particular, we formulate a Deep Reinforcement Active Learning (DRAL) method to guide an agent (a model in a reinforcement learning process) in selecting training samples on-the-fly by a human user/annotator. The reinforcement learning reward is the uncertainty value of each human selected sample. A binary feedback (positive or negative) labelled by the human annotator is used to select the samples of which are used to fine-tune a pre-trained CNN Re-ID model. Extensive experiments demonstrate the superiority of our DRAL method for deep reinforcement learning based human-in-the-loop person Re-ID when compared to existing unsupervised and transfer learning models as well as active learning models.

The classification process is also used in artificial intelligence (AI), which is intelligence created by a computer, so that it can mimic actions like humans in general and can capture events that occur in the surrounding environment. Seeing the very high development of the international coffee trade, it can be concluded that if there is a type of coffee that has the best quality, it will be sought after by coffee importing countries. Batik is cloth that is painted using canting and liquid wax to form motifs or patterns that have high artistic value. Batik has a variety of unique and distinctive patterns that reflect the region where the batik motif originates. One area that has batik motifs in Indonesia is batik in the North Coastal Region of Java Island. In this area, various batiks are produced according to the characteristics of the area itself. Regarding information related to the introduction of types of batik motifs, perhaps it comes from people who have batik skills and batik craftsmen who best understand batik as a whole, while the general public does not really know about batik motifs. Because batik has different motifs and batik motifs in some areas have motifs that are almost uniform but not the same. One of the technologies that can be used is deep learning. The purpose of this study is to propose a Convolutional Neural Network (CNN) and Transfer Learning (TL) model to be implemented in an intelligent system for the process of image classification of coffee bean types. The method used in this study is the PSOCNN transfer learning model VGG16 From the results of tests carried out on 2 models, namely the CNN model, the PSOCNN transfer learning model VGG16. it was found that the highest accuracy was obtained when classifying batik motives images using the PSOCNN-transfer learning model VGG16, which was 83%. The level of accuracy that is increased when compared to the usual CNN model indicates that the use of transfer learning has a good effect on the level of accuracy obtained. Although an increase of 6% is significant, but with this increase it opens up opportunities to increase even higher by using other transfer learning models

Adaptive Attention-Aware Network for unsupervised person re-identification

Abstract. Person Re-Identification (Re-ID) is the task of matching the same person in multiple images captured by different cameras. Recently deep learning-based Re-ID algorithms demonstrated an exciting progress for terrestrial-based cameras, still, person Re-ID in aerial images poses multiple challenges including occlusion of human feature parts, image distortion, and dynamic camera location. In this paper, we propose a new Person Aerial Re-ID framework Robust to Occlusion and Thermal imagery (ParrotGAN). Our model is focused on cross-modality person Re-ID in aerial images. Furthermore, we collected a new large-scale synthetic multimodal AerialReID dataset with 30k images and 137 person ID. Our ParrotGAN model leverages two strategies to achieve robust performance in the task of person Re-ID in thermal and visible range. Firstly, we use a latent space of StyleGAN2 model to estimate the distance between two images of a person. Specifically, we project each real image into the latent space with a correspondent latent vector z. We use the distance between latent vectors to provide a Re-ID similarity metric. Secondly, we use a generative-adversarial network to translate a color image to a synthetic thermal image. We use synthetic image for a cross-modality Re-ID. We evaluate our ParrotGAN model and basleines on our AerialReID and PRAI-1581 datasets. The results of the evaluation are encouraging and demonstrate that our ParrotGAN model competes with baselines in visible range aerial person Re-ID and outperforms them in the cross-modality setting. We made our code and dataset publicly available.

This paper proposes an English-Chinese machine translation research method based on transfer learning. First, it expounds the theory of neural machine translation and transfer learning and related technologies. Neural machine translation is discussed, the advantages and disadvantages of various models are introduced, and the transformer neural machine translation model framework is selected. For low-resource Chinese-English parallel corpus and Tibetan-Chinese parallel corpus, 30 million Chinese-English parallel corpora, 100,000 Chinese-English low-resource parallel corpora, and 100,000 Tibetan-Chinese parallel corpora were used to pretrain the transformer machine translation architecture. The decoders are all composed of 6 identical hidden layers, the initialization of the model parameters is done by the transformer uniform distribution, and the model training uses Adam as the optimizer. In the model transfer part, the parameters with the better effect of the pretrained model are transferred to the low-resource Chinese-English and Tibetan-Chinese machine translation model training, so as to achieve the purpose of knowledge transfer. The results show that the model transfer learning of low-resource Chinese-English parallel corpus improves the translation system's translation by 3.97 BLEU values compared with the translation system without transfer learning at 0.34 BLEU values. Model transfer learning on low-resource Tibetan-Chinese parallel corpus increases the BLEU value by 2.64 BLEU compared to the translation system without transfer learning. The neural machine translation system that uses BPE technology for preprocessing plus model transfer learning is compared to the translation system that only performs transfer learning and shows an improved 0.26 BLEU value.It is verified that the transfer learning method proposed in this paper has a certain improvement in the effect of low-resource Chinese-English and Tibetan-Chinese neural machine translation models.

Breast cancer (BC) is the second leading cause of cancer-related death among women in the United States. Previous studies have shown that African American (AA) women have disproportionately high mortality rate in BC compared to European American (EA) women in the United States. Existing studies have suggested that transfer learning could reduce health disparities in BC by transferring information from a majority group (e.g., EA women) to a minority group (e.g., AA women). However, their performance may be decreased due to limited training patient samples and using single-omics data only. We recently presented a transfer learning method by integrating two multi-omics data for reducing cancer disparities. However, the integration model was not optimized, and its performance in reducing disparities was not robust. To address these concerns, we propose a novel weighted multi-modal transfer learning model that can optimize the integration of multi-omics data to alleviate racial disparities in BC. Specifically, we first calculated the patient-patient similarity by using the Pearson Correlation Coefficient (PCC), based on which we performed weighted integration of multi-omics data. Then, we performed a nested grid search method to find the optimal weights for each type of omics data, which were subsequently fed into a transfer learning model. To demonstrate the effectiveness of our model, we performed the tasks of predicting Disease-Specific Survival (DSS) prognosis for the 1098 female BC patient samples from The Cancer Genome Atlas (TCGA) database. Results suggested that our model with optimized weighted integration of three multi-omics (including mRNA, miRNA and methylation) data significantly outperformed previous multi-omics transfer learning models in terms of AUC. In addition, our multi-modal transfer learning model performed remarkably better than single-omics and two-omics-integration transfer learning models, suggesting that the inclusion of more diverse omics data contributes to a better reduction of racial disparities in BC. Furthermore, the performance of our transfer learning model was also superior to that of conventional mixed models and independent models. In summary, our proposed weighted multi-modal transfer learning model achieves far better performance than existing state-of-the-art methods for reducing health disparities in BC. We expect that our proposed model will provide a new way to reduce health disparities in BC diagnosis, prognosis, and treatment, and it can be extensible to alleviate health disparities in other types of cancer. Citation Format: Min-jeong Baek, Lusheng Li, Jieqiong Wang, Vimla Band, Shibiao Wan. A weighted multi-modal transfer learning model for alleviating racial disparities in breast cancer [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2025; Part 1 (Regular Abstracts); 2025 Apr 25-30; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2025;85(8_Suppl_1):Abstract nr 3620.

Transfer learning is a subfield of machine learning that leverages proficiency in one or more prediction tasks to improve proficiency in a related task. For chemical property prediction, transfer learning models represent a promising approach for addressing the data scarcity limitations of many properties by utilizing potentially abundant data from one or more adjacent applications. Transfer learning models typically utilize a latent variable that is common to several prediction tasks and provides a mechanism for information exchange between tasks. For chemical applications, it is still largely unknown how correlation between the prediction tasks affects performance, the limitations on the number of tasks that can be simultaneously trained in these models before incurring performance degradation, and if transfer learning positively or negatively affects ancillary model properties. Here we investigate these questions using an autoencoder latent space as a latent variable for transfer learning models for predicting properties from the QM9 data set that have been supplemented with semiempirical quantum chemistry calculations. We demonstrate that property prediction can be counterintuitively improved by utilizing a simpler linear predictor model, which has the effect of forcing the latent space to organize linearly with respect to each property. In data scarce prediction tasks, the transfer learning improvement is dramatic, whereas in data rich prediction tasks, there appears to be little adverse impact of transfer learning on prediction performance. The transfer learning approach demonstrated here thus represents a highly advantageous supplement to property prediction models with no downside in implementation.

Deep learning-based fault diagnosis of servo motor bearing using the attention-guided feature aggregation network

In recent years, deep learning has achieved remarkable advancements in medical image analysis, particularly through Convolutional Neural Networks (CNNs) and Transformer-based architectures. This study aims to evaluate and compare the performance of five transfer learning models (DenseNet169, InceptionV3, MobileNetV2, VGG16 and Xception) and a Vision Transformer (ViT) model for the classification of skin cancer using the “Skin Cancer: Malignant vs. Benign” dataset .In the first phase, the ViT model achieved the highest overall performance with 93.79% recall, 92.22% precision, 93.00% F1-score and 92.42% accuracy. Although InceptionV3 and MobileNetV2 demonstrated strong recall values, they did not match the overall accuracy of ViT. In the second phase, image enhancement techniques—grayscale conversion, thresholding, Canny edge detection, dilation, and erosion were applied to emphasize lesion boundaries and improve contrast. Using these enhanced images, the ViT model again achieved the best performance, with 95.49% recall, 94.17% precision, 94.83% F1-score, and 94.39% accuracy. These results indicate that the ViT architecture provides superior accuracy and reliability in complex and enhanced medical images. Furthermore, the study demonstrates that incorporating image preprocessing techniques can significantly enhance the performance of deep learning models in medical imaging applications.

This study aimed to compare the axial cranial ultrasound images of normal and open neural tube defect (NTD) fetuses using a deep learning (DL) model and to assess its predictive accuracy in identifying open NTD.It was a prospective case-control study. Axial trans-thalamic fetal ultrasound images of participants with open fetal NTD and normal controls between 14 and 28 weeks of gestation were taken after consent. The images were divided into training, testing, and validation datasets randomly in the ratio of 70:15:15. The images were further processed and classified using DL convolutional neural network (CNN) transfer learning (TL) models. The TL models were trained for 50 epochs. The data was analyzed in terms of Cohen kappa score, accuracy score, area under receiver operating curve (AUROC) score, F1 score validity, sensitivity, and specificity of the test.A total of 59 cases and 116 controls were fully followed. Efficient net B0, Visual Geometry Group (VGG), and Inception V3 TL models were used. Both Efficient net B0 and VGG16 models gave similar high training and validation accuracy (100 and 95.83%, respectively). Using inception V3, the training and validation accuracy was 98.28 and 95.83%, respectively. The sensitivity and specificity of Efficient NetB0 was 100 and 89%, respectively, and was the best.The analysis of the changes in axial images of the fetal cranium using the DL model, Efficient Net B0 proved to be an effective model to be used in clinical application for the identification of open NTD. · Open spina bifida is often missed due to the nonrecognition of the lemon sign on ultrasound.. · Image classification using DL identified open spina bifida with excellent accuracy.. · The research is clinically relevant in low- and middle-income countries..

IntroductionPancreaticoduodenectomy (PD) for patients with pancreatic ductal adenocarcinoma (PDAC) is associated with a high risk of postoperative complications (PoCs) and risk prediction of these is therefore critical for optimal treatment planning. We hypothesize that novel deep learning network approaches through transfer learning may be superior to legacy approaches for PoC risk prediction in the PDAC surgical setting.MethodsData from the US National Surgical Quality Improvement Program (NSQIP) 2002–2018 were used, with a total of 5,881,881 million patients, including 31,728 PD patients. Modelling approaches comprised of a model trained on a general surgery patient cohort and then tested on a PD specific cohort (general model), a transfer learning model trained on the general surgery patients with subsequent transfer and retraining on a PD-specific patient cohort (transfer learning model), a model trained and tested exclusively on the PD-specific patient cohort (direct model), and a benchmark random forest model trained on the PD patient cohort (RF model). The models were subsequently compared against the American College of Surgeons (ACS) surgical risk calculator (SRC) in terms of predicting mortality and morbidity risk.ResultsBoth the general model and transfer learning model outperformed the RF model in 14 and 16 out of 19 prediction tasks, respectively. Additionally, both models outperformed the direct model on 17 out of the 19 tasks. The transfer learning model also outperformed the general model on 11 out of the 19 prediction tasks. The transfer learning model outperformed the ACS-SRC regarding mortality and all the models outperformed the ACS-SRC regarding the morbidity prediction with the general model achieving the highest Receiver Operator Area Under the Curve (ROC-AUC) of 0.668 compared to the 0.524 of the ACS SRC.ConclusionDNNs deployed using a transfer learning approach may be of value for PoC risk prediction in the PD setting.

Key Smart City applications such as traffic management and public security rely heavily on the intelligent processing of video and image data, often in the form of visual retrieval tasks, such as person Re-IDentification (ReID) and vehicle re-identification. For these tasks, Deep Neural Networks (DNNs) have been the dominant solution for the past decade, for their remarkable ability in learning discriminative features from images to boost retrieval performance. However, it is been discovered that DNNs are broadly vulnerable to maliciously constructed adversarial examples. By adding small perturbations to a query image, the returned retrieval results will be completely dissimilar from the query image. This poses serious challenges to vital systems in Smart City applications that depend on the DNN-based visual retrieval technology, as in the physical world, simple camouflage can be added on the subject (a few patches on the body or car), and turn the subject completely untrackable by person or vehicle Re-ID systems. To demonstrate the potential of such threats, this paper proposes a novel adversarial patch generative adversarial network (AP-GAN) to generate adversarial patches instead of modifying the entire image, which also causes the DNNs-based image retrieval models to return incorrect results. AP-GAN is trained in an unsupervised way that requires only a small amount of unlabeled data for training. Once trained, it produces query-specific perturbations for query images to form adversarial queries. Extensive experiments show that the AP-GAN achieves excellent attacking performance with various application scenarios that are based on deep features, including image retrieval, person ReID and vehicle ReID. The results of this study provide a warning that when deploying a DNNs-based image retrieval system, its security and robustness needs to be thoroughly considered.

Integrating adaptive input length selection strategy and unsupervised transfer learning for bearing fault diagnosis under noisy conditions

To improve the function of machine translation to adapt to global language translation, the work takes deep neural network (DNN) as the basic theory, carries out transfer learning and neural network translation modeling, and optimizes the word alignment function in machine translation performance. First, the work implements a deep learning translation network model for English translation. On this basis, the neural machine translation model is designed under transfer learning. The random shielding method is introduced to implement the language training model, and the machine translation is slightly adjusted as the goal of transfer learning, thereby improving the semantic understanding ability in translation performance. Meanwhile, the work design introduces the method of word alignment optimization and optimizes the performance of word alignment in the transformer system by using word corpus. The experimental results show that the proposed method reduces the average alignment error rate by 8.1%, 24.4%, and 22.1% in EnRo (English-Roman), EnGe (English-German), and EnFr (English-French), respectively, compared with the previous algorithms. Compared with the designed optimization method, the word alignment error rate is lower than that of traditional methods. The modeling and optimization method is feasible, which can effectively solve the problems of insufficient information utilization, large parameter scale, and difficult storage in the process of machine translation. Additionally, it provides a feasible idea and direction for the optimization and improvement in neural machine translation (NMT) system.