OoDBench+:量化和理解分发外泛化的两个维度
IEEE transactions on pattern analysis and machine intelligence
|November 3, 2025
概括
本研究介绍了两种分布转移,即多样性转移和相关性转移,这对于理解深度学习中的外分布 (OoD) 概括至关重要. 这些转变定义了性能界限,并解释了不同数据集中的算法限制.
科学领域:
- 人工智能的人工智能
- 机器学习 机器学习
- 计算机视觉 计算机视觉
背景情况:
- 深度学习的优势在于独立且相同分布的 (i.i.d.) 数据. 数据. 数据.
- 在数据分布不同的情况下,分布外 (OoD) 泛化带来了重大挑战.
- 目前对OoD概括算法的评估方法有限.
研究的目的:
- 确定和正式定义两种主要类型的分布转移:多样性转移和相关性转移.
- 分析这些转变如何影响分布外概括算法的性能.
- 提供一个统一的框架,用于在各种数据集和任务中评估OoD概括.
主要方法:
- 多样性转移和相关性转移的正式定义.
- 在数据集上对现有的OoD概括算法的实证评估,这些数据集以每个轮班类型为主.
- 对归因于定义的班次的性能下降的分析.
主要成果:
- 多样性和相关性转移在OoD数据集和上限算法性能中无处不在.
- 现有的OOD算法对每个轮班类型都有不同的强度和局限性.
- 在OOD设置中的所有性能下降都可以通过这两个定义的变化来解释.
结论:
- 拟议的多样性和相关性转移提供了对分布外泛化挑战的基本理解.
- 这项工作为评估和开发更强大的OoD概括算法建立了基准.
- 这些发现为未来研究跨不同数据分布的可靠深度学习铺平了道路.
相关概念视频
Quantifying and Rejecting Outliers: The Grubbs Test
3.5K
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...
3.5K
What Are Outliers?
4.9K
Outliers are observed data points that are far from the least squares line. They have unusual values and need to be examined carefully. Though an outlier may result from erroneous data, at other times, it may hold valuable information about the population under study and should be included in the data. Hence, it is crucial to examine what causes a data point to be an outlier.
The z score is used to find outliers or unusual values. It should be noted that any values beyond -2 and +2 are...
The z score is used to find outliers or unusual values. It should be noted that any values beyond -2 and +2 are...
4.9K
Applications of Normal Distribution
8.9K
The normal distribution is a useful statistical tool. One of its practical applications is determining the door height after considering the normal distribution of heights of persons, such that many can pass through it easily without striking their heads. The normal distribution can also determine the probability of a person having a height less than a specific height.
The heights of 15 to 18-year-old males from Chile from 1984 to 1985 followed a normal distribution. The mean height is 172.36...
The heights of 15 to 18-year-old males from Chile from 1984 to 1985 followed a normal distribution. The mean height is 172.36...
8.9K
Detection of Gross Error: The Q Test
6.8K
When one or more data points appear far from the rest of the data, there is a need to determine whether they are outliers and whether they should be eliminated from the data set to ensure an accurate representation of the measured value. In many cases, outliers arise from gross errors (or human errors) and do not accurately reflect the underlying phenomenon. In some cases, however, these apparent outliers reflect true phenomenological differences. In these cases, we can use statistical methods...
6.8K
Generalization, Discrimination, and Extinction
1.3K
Generalization, discrimination, and extinction are key concepts in operant conditioning that influence how behaviors are learned and maintained.
Generalization occurs when a behavior reinforced in one context is performed in similar situations. For instance, a student who studies diligently for calculus and receives excellent grades might apply the same study habits to psychology and history, expecting similar results. Generalization shows how learning in one setting can influence behavior in...
Generalization occurs when a behavior reinforced in one context is performed in similar situations. For instance, a student who studies diligently for calculus and receives excellent grades might apply the same study habits to psychology and history, expecting similar results. Generalization shows how learning in one setting can influence behavior in...
1.3K
Unusual Results
3.7K
Unusual results are those that have a very low chance of occurring. Unusual results can be identified using probabilities and the range rule of thumb. In problems involving probability, unusual results can be observed in 2 instances – an unusually high number of successes or an unusually low number of successes.
According to the range rule of thumb, any value above or below two standard deviations, 2σ from the mean, μ is considered unusual.
Maximum unusual value =...
According to the range rule of thumb, any value above or below two standard deviations, 2σ from the mean, μ is considered unusual.
Maximum unusual value =...
3.7K

