关于征服野生分布外检测检测的两个方面
IEEE transactions on pattern analysis and machine intelligence
|February 24, 2026
概括
本研究涉及野生分布外 (OOD) 检测,其中OOD数据包含分布内 (ID) 语义. 新的方法可以动态估计真正的ID/OOD指标,并重新采样数据,以提高开放世界分类中的模型可靠性.
科学领域:
- 机器学习 机器学习
- 计算机视觉 计算机视觉
- 人工智能的人工智能
背景情况:
- 分布外 (OOD) 检测对于开放世界分类至关重要,识别数据从语义上与分布内 (ID) 数据不同.
- 异常值暴露 (OE) 通过在训练期间包括OD数据来改善OD检测.
- 野生OOD检测,OOD数据包含ID语义,损害了模型可靠性,但研究不足.
研究的目的:
- 从实例和分布的角度理论分析野生OOD检测的挑战.
- 引入通用解决方案,以在OOD数据中存在ID语义时提高OOD检测可靠性.
- 开发一个统一的框架,整合强大的野生OOD检测的互补解决方案.
主要方法:
- 实例方面:一个框架,从野生的OD数据动态估计真正的ID/OOD指标,减轻错误标签.
- 分布方面:一个重新抽样方案,以 ID 分布为指导,从野生 OOD 数据中删除潜在的 ID 子分布.
- 将这两种方法整合到一个统一的框架中,具有理论保障和实际算法.
主要成果:
- 拟议的方法有效地减轻了错误标记实例和误导性ID子分布在野生OOD数据中的负面影响.
- 综合实证评估表明,与现有的先进方法相比,其性能和可靠性更高.
- 统一框架利用互补的优势提高了野生OOD检测效率.
结论:
- 开发的方法为野生OOD检测的关键问题提供了强有力的解决方案.
- 理论分析和实践算法在开放世界分类可靠性方面取得了重大进展.
- 这项工作为更可靠的AI系统在复杂的现实场景中铺平了道路.
更多相关视频
08:23Single Droplet Digital Polymerase Chain Reaction for Comprehensive and Simultaneous Detection of Mutations in Hotspot Regions
Published on: September 25, 2018
14.1K
10:41Wild-type Blocking PCR Combined with Direct Sequencing as a Highly Sensitive Method for Detection of Low-Frequency Somatic Mutations
Published on: March 29, 2017
12.4K
相关概念视频
Distribution Reliability and Automation
542
Distribution reliability in electrical power systems is critical for ensuring an uninterrupted power supply to consumers at minimal cost. According to IEEE Standard Terms, reliability is the probability that a device will function without failure over a specified time period or amount of usage. For electric power distribution, this translates to maintaining continuous power supply and addressing customer concerns over power outages. Several indices, as defined by IEEE Standard 1366-2012, are...
542
Difference from Background: Limit of Detection
8.6K
The limit of detection (LOD) is the smallest amount of analyte that can be distinguished from the background noise. The LOD value corresponds to the concentration at which the analyte signal is three times larger than the standard deviation of the blank signal. Below this value, the analyte signal cannot be differentiated from the background noise. It is calculated by dividing the calibration slope by 3 times the standard deviation of the blank signals.
The LOD indicates the presence or absence...
The LOD indicates the presence or absence...
8.6K
Censoring Survival Data
609
Survival analysis is a statistical method used to analyze time-to-event data, often employed in fields such as medicine, engineering, and social sciences. One of the key challenges in survival analysis is dealing with incomplete data, a phenomenon known as "censoring." Censoring occurs when the event of interest (such as death, relapse, or system failure) has not occurred for some individuals by the end of the study period or is otherwise unobservable, and it might have many different...
609
Quantifying and Rejecting Outliers: The Grubbs Test
4.2K
Sometimes, a data set can have a recorded numerical observation that greatly deviates from the rest of the data. Assuming that the data is normally distributed, a statistical method called the Grubbs test can be used to determine whether the observation is truly an outlier. To perform a two-tailed Grubbs test, first, calculate the absolute difference between the outlier and the mean. Then, calculate the ratio between this difference and the standard deviation of the sample. This...
4.2K
Masking and Demasking Agents
3.7K
EDTA titrations may necessitate masking and demasking agents to temporarily protect a particular metal ion in a mixture from the EDTA reaction. These agents facilitate the sequential analysis of the metal ions by forming stable complexes with some—but not all—metal ions during certain steps.
There are many masking agents, such as cyanide, fluoride, triethanolamine, thiourea, and 2,3-bis(sulfanyl)propan-1-ol (formerly 2,3-dimercapto-1-propanol), with the masking agent chosen based on...
There are many masking agents, such as cyanide, fluoride, triethanolamine, thiourea, and 2,3-bis(sulfanyl)propan-1-ol (formerly 2,3-dimercapto-1-propanol), with the masking agent chosen based on...
3.7K
Types of Errors: Detection and Minimization
11.6K
Error is the deviation of the obtained result from the true, expected value or the estimated central value. Errors are expressed in absolute or relative terms.
Absolute error in a measurement is the numerical difference from the true or central value. Relative error is the ratio between absolute error and the true or central value, expressed as a percentage.
Errors can be classified by source, magnitude, and sign. There are three types of errors: systematic, random, and gross.
Systematic or...
Absolute error in a measurement is the numerical difference from the true or central value. Relative error is the ratio between absolute error and the true or central value, expressed as a percentage.
Errors can be classified by source, magnitude, and sign. There are three types of errors: systematic, random, and gross.
Systematic or...
11.6K
