在基于图像的推断中平衡错误分类错误,使用问题域语义和嵌套级联架构
Xin Du1, Rajesh Jena1,2, Katayoun Farrahi3
1RadNet Data Science Team, The Cavendish Laboratory, University of Cambridge, Cambridge, UK.
Neural computing & applications
|October 21, 2025
概括
本研究介绍了神经网络的级联学习,优先考虑关键错误分类. 通过考虑错误严重程度和类层次,模型可以更好地处理模式识别任务中昂贵的错误.
科学领域:
- 机器学习 机器学习
- 计算机科学 计算机科学
背景情况:
- 传统的模式识别模型优先考虑分类准确性.
- 现有的方法往往忽略了与不同类型的错误分类错误相关的不同成本.
- 错误分类成本可以从专家知识或类标签的语义分析中得出.
研究的目的:
- 开发一个深度的神经架构,可以解释不同的错误分类成本.
- 利用类标签的等级结构来提高模型性能.
- 引入一个性能指标,考虑错误的严重程度.
主要方法:
- 实现了一个深度的神经架构,以嵌套的,层层明智的方式 (级联学习) 进行训练.
- 将该方法应用于来自图像和表格域的五个不同的例子.
- 利用一种叫做"严重性"的绩效衡量方法来指导训练中的错误.
主要成果:
- 证明级联学习可以有效地利用类标签的层次方面.
- 展示了如何强调在层次结构中更深层次的类的学习.
- 成功地消除了语义上相似或邻近类之间的错误.
结论:
- 级联学习提供了一种新的方法来解决神经网络中的错误分类成本.
- 考虑错误严重程度和类层次导致更强大和成本意识的机器学习系统.
- 这种方法对在真实应用中部署机器学习具有重大意义,因为错误成本各不相同.
相关概念视频
Survival Tree
383
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
Building a Survival Tree
Constructing a...
Building a Survival Tree
Constructing a...
383
Classification of Systems-I
545
Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
545
Classification of Systems-II
457
Continuous-time systems have continuous input and output signals, with time measured continuously. These systems are generally defined by differential or algebraic equations. For instance, in an RC circuit, the relationship between input and output voltage is expressed through a differential equation derived from Ohm's law and the capacitor relation,
457

