Evidential Deep Learning
PulseAugur coverage of Evidential Deep Learning — every cluster mentioning Evidential Deep Learning across labs, papers, and developer communities, ranked by signal.
-
新框架简化了用于不确定性估计的证据深度学习
研究人员开发了一个简化的证据深度学习（EDL）框架，使不确定性估计在计算上更有效率。这种新方法用在狄利克雷均值处评估的插件损失来近似EDL的目标，使用标准的深度学习工具更容易实现。该框架将标准softmax分类器作为一个特例，并在Google Speech Commands数据集上进行了验证，取得了与经典EDL相当的性能。
-
AI model classifies wildfire smoke density with uncertainty estimates
Researchers have developed a new deep learning framework to classify wildfire smoke density from satellite imagery, categorizing it into light, moderate, and heavy severity. This model provides decomposed epistemic and …
-
New research reveals flaws in AI model OOD detection evaluation methods
A new paper published on arXiv introduces a critical finding regarding the evaluation of Out-of-Distribution (OOD) detection in Evidential Deep Learning (EDL). The research demonstrates that the common metric of 'vacuit…
-
GEM-FI: Gated Evidential Mixtures with Fisher Modulation
Researchers have introduced GEM-FI, a novel family of models designed to improve uncertainty estimation in deep learning. This approach addresses limitations of existing Evidential Deep Learning methods, which can be ov…
-
New framework uses Evidential Deep Learning for uncertainty-aware pedestrian attribute recognition
Researchers have developed UAPAR, a novel framework for pedestrian attribute recognition that incorporates Evidential Deep Learning (EDL) to assess prediction reliability. This approach aims to improve system robustness…
-
CMGL框架通过置信度引导的多组学图学习改进癌症亚型分类
研究人员开发了CMGL，一种用于癌症亚型分类的新型框架，该框架利用多组学数据。这种两阶段方法首先使用证据深度学习估计每个患者不同组学模态的可靠性。然后，这些置信度分数指导组学数据的融合和患者相似性图的构建，从而提高癌症亚型分类的准确性。CMGL在多项癌症任务中表现出优越的性能，包括一个32类全癌分类任务，并显示出将学习到的表示转移到新癌症类型的潜力。