Crest: Cross-modal resonance through evidential deep learning for enhanced zero-shot learning
Zero-shot learning (ZSL) enables the recognition of novel classes by leveraging semantic
knowledge transfer from known to unknown categories. This knowledge, typically …
knowledge transfer from known to unknown categories. This knowledge, typically …
A Comprehensive Survey on Evidential Deep Learning and Its Applications
Reliable uncertainty estimation has become a crucial requirement for the industrial
deployment of deep learning algorithms, particularly in high-risk applications such as …
deployment of deep learning algorithms, particularly in high-risk applications such as …
[HTML][HTML] Semi-supervised object detection with uncurated unlabeled data for remote sensing images
Annotating remote sensing images (RSIs) poses a significant challenge, primarily due to its
labor-intensive nature. Semi-supervised object detection (SSOD) methods address this …
labor-intensive nature. Semi-supervised object detection (SSOD) methods address this …
Evidential deep partial multi-view classification with discount fusion
H Huang, Z Liu, S Letchmunan, M Deveci, M Lin… - arXiv preprint arXiv …, 2024 - arxiv.org
Incomplete multi-view data classification poses significant challenges due to the common
issue of missing views in real-world scenarios. Despite advancements, existing methods …
issue of missing views in real-world scenarios. Despite advancements, existing methods …
Trusted unified feature-neighborhood dynamics for multi-view classification
Multi-view classification (MVC) faces inherent challenges due to domain gaps and
inconsistencies across different views, often resulting in uncertainties during the fusion …
inconsistencies across different views, often resulting in uncertainties during the fusion …