In the imbalance data scenarios, Deep Neural Networks (DNNs) fail to generalize well on minority classes. In this letter, we propose a simple and effective learning function i.e, Visually Interpretable Space Adjustment Learning (VISAL) to handle the imbalanced data classification task. VISAL's objective is to create more room for the generalization of minority class samples by bringing in both the angular and euclidean margins into the cross-entropy learning strategy. When evaluated on the imbalanced versions of CIFAR, Tiny ImageNet, COVIDx and IMDB reviews datasets, our proposed method outperforms the state of the art works by a significant margin.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.neunet.2023.01.015 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Hybrid Data Augmentation Strategies for Robust Deep Learning Classification of Corneal Topographic MapTopographic Map.
Biomed Phys Eng Express
January 2025
National School of Electronics and Telecommunication of Sfax, Sfax rte mahdia, sfax, sfax, 3012, TUNISIA.
Deep learning has emerged as a powerful tool in medical imaging, particularly for corneal topographic map classification. However, the scarcity of labeled data poses a significant challenge to achieving robust performance. This study investigates the impact of various data augmentation strategies on enhancing the performance of a customized convolutional neural network model for corneal topographic map classification.
View Article and Find Full Text PDFDeveloping a Machine Learning-Based Automated Patient Engagement Estimator for Telehealth: Algorithm Development and Validation Study.
JMIR Form Res
January 2025
Department of Computer Science, Purdue University, West Lafayett, IN, United States.
Background: Patient engagement is a critical but challenging public health priority in behavioral health care. During telehealth sessions, health care providers need to rely predominantly on verbal strategies rather than typical nonverbal cues to effectively engage patients. Hence, the typical patient engagement behaviors are now different, and health care provider training on telehealth patient engagement is unavailable or quite limited.
View Article and Find Full Text PDFThe Canadian Genomics Research and Development Initiative for Antimicrobial Resistance (GRDI-AMR) uses a genomics-based approach to understand how health care, food production and the environment contribute to the development of antimicrobial resistance. Integrating genomics contextual data streams across the One Health continuum is challenging because of the diversity in data scope, content and structure. To better enable data harmonization for analyses, a contextual data standard was developed.
View Article and Find Full Text PDFPerfusion estimation from dynamic non-contrast computed tomography using self-supervised learning and a physics-inspired U-net transformer architecture.
Int J Comput Assist Radiol Surg
January 2025
Department of Biomedical Engineering, The University of Texas at Austin, Austin, TX, USA.
Purpose: Pulmonary perfusion imaging is a key lung health indicator with clinical utility as a diagnostic and treatment planning tool. However, current nuclear medicine modalities face challenges like low spatial resolution and long acquisition times which limit clinical utility to non-emergency settings and often placing extra financial burden on the patient. This study introduces a novel deep learning approach to predict perfusion imaging from non-contrast inhale and exhale computed tomography scans (IE-CT).
View Article and Find Full Text PDFDeep learning-based MVIT-MLKA model for accurate classification of pancreatic lesions: a multicenter retrospective cohort study.
Radiol Med
January 2025
Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, 400016, China.
Background: Accurate differentiation between benign and malignant pancreatic lesions is critical for effective patient management. This study aimed to develop and validate a novel deep learning network using baseline computed tomography (CT) images to predict the classification of pancreatic lesions.
Methods: This retrospective study included 864 patients (422 men, 442 women) with confirmed histopathological results across three medical centers, forming a training cohort, internal testing cohort, and external validation cohort.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!