我们真的需要子吗? 分段损失的隐藏的区域大小偏差
Bingyuan Liu1, Jose Dolz2, Adrian Galdran3
1LIVIA, ÉTS Montréal, Canada; International Laboratory on Learning Systems (ILLS), McGill - ETS - MILA - CNRS - Université Paris-Saclay - CentraleSupélec, Canada.
Medical image analysis
|November 2, 2023
概括
在细分中常见的交叉 (CE) 和子损失,与以前认为的更为深层次的联系. 这项研究揭示了他们的偏见,并提出了一种控制区域大小偏差以改善细分性能的方法.
科学领域:
- 计算机视觉 计算机视觉
- 机器学习 机器学习
- 医疗成像医学成像
背景情况:
- 像交叉 (CE) 和子这样的细分损失被广泛使用,但它们的关系和最佳应用仍在争论中.
- 现有研究表明,CE和Dice是互补的,导致复合损失函数,但它们的基础理论连接尚未完全理解.
研究的目的:
- 提供理论分析,揭示CE和Dice细分损失之间的深层联系.
- 解释CE和Dice在不同数据集和应用中观察到的性能变化.
- 提出一种新的方法来控制细分损失中的区域大小偏差.
主要方法:
- 使用受约束优化,有限关系和信息理论方法进行理论分析.
- 将CE和Dice损失分解为基本真相匹配和区域大小的罚款条款.
- 开发一种以原则为基础的方法,将CE与L1或KL分歧项整合在一起,以控制区域大小偏差.
主要成果:
- CE和Dice的损失具有共同的结构,具有明显的区域大小偏差:Dice倾向于不平衡的解决方案,而CE则鼓励基本真相比例.
- 理论发现解释了Dice在失衡的医学成像中的成功,以及CE在自然图像中的优势.
- 提出的方法有效地控制了区域大小偏差,在不牺牲一般性的情况下减轻了阶级不平衡.
结论:
- CE和Dice的损失基本上是通过其区域大小的罚款组件联系在一起的.
- 对区域大小偏差的明确控制提供了一种原则性的方法来提高细分性能,特别是在不平衡的场景中.
- 拟议的集成损失函数在各种应用中证明了有效性,验证了理论分析.
相关概念视频
01:18Reducing Line Loss
156
In a three-phase circuit, line loss is an indicator of energy dissipated as heat due to the resistance of transmission lines. To address this, incorporating transformers into the system—a step-up transformer at the source and a step-down transformer at the load—is a strategic solution. Two three-phase transformers are introduced to improve this.
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
156
01:05Difference from Background: Limit of Detection
6.4K
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...
6.4K
01:27Margin of Error
4.1K
The margin of error is also called the maximum error of an estimate. The margin of error is the maximum possible or expected difference between the observed sample parameter value and the actual population parameter value. For proportion, it is the maximum difference between the value of sample proportion obtained from the data and the true value of population proportion. As the true value of the population parameter is not known, the margin of error is calculated using the sample statistic.
4.1K