Out Of Distribution Detection
PulseAugur coverage of Out Of Distribution Detection — every cluster mentioning Out Of Distribution Detection across labs, papers, and developer communities, ranked by signal.
1 天有情绪数据
-
新方法改进了视觉语言模型的分布外检测
研究人员开发了一种新方法，以改进预训练的视觉语言模型（VLMs）的分布外（OOD）检测。该技术通过纠正采样偏差来解决识别语义上不同的负面标签的挑战。这种可转换为蒙特卡洛采样的去偏负面挖掘方法，在OOD检测设置中确立了新的最先进水平。
-
新的分布外检测方法展现出领先性能和效率提升
研究人员开发了一种名为ConjNorm的新型分布外（OOD）检测方法，该方法将密度函数设计重新构建为优化范数系数。该方法在OOD检测基准测试中展现出领先性能，显著优于先前的方法。与此同时，一项比较研究发现，传统的机器学习方法在分布外检测方面可以达到与深度学习方法相媲美的性能，尤其是在医学影像等视觉复杂度较低的领域，同时提供更高的计算效率和更低的延迟。
-
ML matches DL accuracy in OOD detection, offers better efficiency
A new study comparing machine learning (ML) and deep learning (DL) for out-of-distribution (OOD) detection found that both approaches achieved near-perfect accuracy on medical imaging datasets. While DL models are often…
-
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…