A comprehensive survey of few-shot learning: Evolution, applications, challenges, and opportunities
Few-shot learning (FSL) has emerged as an effective learning method and shows great
potential. Despite the recent creative works in tackling FSL tasks, learning valid information …
potential. Despite the recent creative works in tackling FSL tasks, learning valid information …
A survey on deep learning for cybersecurity: Progress, challenges, and opportunities
As the number of Internet-connected systems rises, cyber analysts find it increasingly difficult
to effectively monitor the produced volume of data, its velocity and diversity. Signature-based …
to effectively monitor the produced volume of data, its velocity and diversity. Signature-based …
Large language models for cyber security: A systematic literature review
The rapid advancement of Large Language Models (LLMs) has opened up new
opportunities for leveraging artificial intelligence in various domains, including cybersecurity …
opportunities for leveraging artificial intelligence in various domains, including cybersecurity …
Few-shot learning with noisy labels
Few-shot learning (FSL) methods typically assume clean support sets with accurately
labeled samples when training on novel classes. This assumption can often be unrealistic …
labeled samples when training on novel classes. This assumption can often be unrealistic …
Few-shot hyperspectral image classification with self-supervised learning
Recently, few-shot learning (FSL) has been introduced for hyperspectral image (HSI)
classification with few labeled samples. However, existing FSL-based HSI classification …
classification with few labeled samples. However, existing FSL-based HSI classification …
Neighborhood collective estimation for noisy label identification and correction
Learning with noisy labels (LNL) aims at designing strategies to improve model performance
and generalization by mitigating the effects of model overfitting to noisy labels. The key …
and generalization by mitigating the effects of model overfitting to noisy labels. The key …
Context-enriched molecule representations improve few-shot drug discovery
A central task in computational drug discovery is to construct models from known active
molecules to find further promising molecules for subsequent screening. However, typically …
molecules to find further promising molecules for subsequent screening. However, typically …
Trans4E: Link prediction on scholarly knowledge graphs
Abstract The incompleteness of Knowledge Graphs (KGs) is a crucial issue affecting the
quality of AI-based services. In the scholarly domain, KGs describing research publications …
quality of AI-based services. In the scholarly domain, KGs describing research publications …
Few-shot rolling bearing fault diagnosis with metric-based meta learning
S Wang, D Wang, D Kong, J Wang, W Li, S Zhou - Sensors, 2020 - mdpi.com
Fault diagnosis methods based on deep learning and big data have achieved good results
on rotating machinery. However, the conventional deep learning method of bearing fault …
on rotating machinery. However, the conventional deep learning method of bearing fault …
[HTML][HTML] Deepfake forensics analysis: An explainable hierarchical ensemble of weakly supervised models
Deepfakes have become exponentially more common and sophisticated in recent years, so
much so that forensic specialists, policy makers, and the public alike are anxious about their …
much so that forensic specialists, policy makers, and the public alike are anxious about their …