小物体定位与90%的注释减少通过积极的未标记的学习
Xiao Zhou1, Shihong Wang2,3, Weiguo Hu1
1Department of Automation, Tsinghua University, Beijing 100084, China.
Micromachines
|December 31, 2025
概括
这项研究引入了一种新的积极无标记 (PU) 学习方法,用于小物体本地化. 它使用最小的点注释实现了高性能,降低了单细胞分析等任务的成本.
科学领域:
- 计算机视觉 计算机视觉
- 机器学习 机器学习
- 图像分析 图像分析
背景情况:
- 小物体的定位很困难,因为视觉外观不佳和数据噪音很大.
- 目前的方法通常依赖于广泛的注释,增加培训成本.
- 人类学习以有限的例子展示了有效的技能获取.
研究的目的:
- 开发一种新的小物体本地化方法,使用正无标记 (PU) 学习.
- 为了实现精确的本地化,显著减少了注释工作.
- 从部分注释数据中模拟类似人类的学习.
主要方法:
- 提出了一种新的正面未标记 (PU) 学习框架.
- 使用部分点注释来训练本地化模型.
- 对各种小型对象数据集 (单细胞,动物/昆虫,人群) 的方法进行了评估.
主要成果:
- 实现了强大的本地化性能,F1得分超过0.75.
- 即使在不到10%的总点注释中,也证明了有效性.
- 在多个具有挑战性的小物体场景中验证了方法.
结论:
- 拟议的PU学习方法为小型对象本地化提供了有效的解决方案.
- 显著降低注释成本,使其适用于数据稀缺的应用程序.
- 允许低注释成本分析,特别是在微流体学中单细胞研究.
相关概念视频
Negative Regulator Molecules
32.1K
Positive regulators allow a cell to advance through cell cycle checkpoints. Negative regulators have an equally important role as they terminate a cell’s progression through the cell cycle—or pause it—until the cell meets specific criteria.
32.1K
Types of Errors: Detection and Minimization
8.7K
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...
8.7K
Detection of Gross Error: The Q Test
7.1K
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...
7.1K
Difference from Background: Limit of Detection
9.0K
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...
9.0K
Mass Analyzers: Overview
2.0K
The mass analyzer is a crucial component of the mass spectrometer. In the ionization chamber, the vaporized sample is bombarded with a high-energy electron beam to generate a radical cation and further fragment into neutral molecules, radicals, and cations. A series of negatively charged accelerator plates accelerate the cations into the mass analyzer. The mass analyzer separates ions according to their mass-to-charge (m/z) ratios and then directs them to the detector. The common types of mass...
2.0K


