Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2506.03158 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916777252880384 |
|---|---|
| author | Qin, Jiahao Peng, Bei Liu, Feng Cheng, Guangliang Zong, Lu |
| author_facet | Qin, Jiahao Peng, Bei Liu, Feng Cheng, Guangliang Zong, Lu |
| contents | Deep learning models frequently encounter feature uncertainty in diverse learning scenarios, significantly impacting their performance and reliability. This challenge is particularly complex in multi-modal scenarios, where models must integrate information from different sources with inherent uncertainties. We propose Dynamic Uncertainty-Aware Learning (DUAL), a unified framework that effectively handles feature uncertainty in both single-modal and multi-modal scenarios. DUAL introduces three key innovations: Dynamic Feature Uncertainty Modeling, which continuously refines uncertainty estimates through joint consideration of feature characteristics and learning dynamics; Adaptive Distribution-Aware Modulation, which maintains balanced feature distributions through dynamic sample influence adjustment; and Uncertainty-aware Cross-Modal Relationship Learning, which explicitly models uncertainties in cross-modal interactions. Through extensive experiments, we demonstrate DUAL's effectiveness across multiple domains: in computer vision tasks, it achieves substantial improvements of 7.1% accuracy on CIFAR-10, 6.5% accuracy on CIFAR-100, and 2.3% accuracy on Tiny-ImageNet; in multi-modal learning, it demonstrates consistent gains of 4.1% accuracy on CMU-MOSEI and 2.8% accuracy on CMU-MOSI for sentiment analysis, while achieving 1.4% accuracy improvements on MISR. The code will be available on GitHub soon. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_03158 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DUAL: Dynamic Uncertainty-Aware Learning Qin, Jiahao Peng, Bei Liu, Feng Cheng, Guangliang Zong, Lu Machine Learning Computer Vision and Pattern Recognition Deep learning models frequently encounter feature uncertainty in diverse learning scenarios, significantly impacting their performance and reliability. This challenge is particularly complex in multi-modal scenarios, where models must integrate information from different sources with inherent uncertainties. We propose Dynamic Uncertainty-Aware Learning (DUAL), a unified framework that effectively handles feature uncertainty in both single-modal and multi-modal scenarios. DUAL introduces three key innovations: Dynamic Feature Uncertainty Modeling, which continuously refines uncertainty estimates through joint consideration of feature characteristics and learning dynamics; Adaptive Distribution-Aware Modulation, which maintains balanced feature distributions through dynamic sample influence adjustment; and Uncertainty-aware Cross-Modal Relationship Learning, which explicitly models uncertainties in cross-modal interactions. Through extensive experiments, we demonstrate DUAL's effectiveness across multiple domains: in computer vision tasks, it achieves substantial improvements of 7.1% accuracy on CIFAR-10, 6.5% accuracy on CIFAR-100, and 2.3% accuracy on Tiny-ImageNet; in multi-modal learning, it demonstrates consistent gains of 4.1% accuracy on CMU-MOSEI and 2.8% accuracy on CMU-MOSI for sentiment analysis, while achieving 1.4% accuracy improvements on MISR. The code will be available on GitHub soon. |
| title | DUAL: Dynamic Uncertainty-Aware Learning |
| topic | Machine Learning Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.03158 |