SFBM:共享特征偏差缓解长尾图像识别
IEEE transactions on neural networks and learning systems
|August 8, 2025
概括
本研究引入了共享特征偏差缓解 (SFBM) 框架,以改进处理不平衡数据集的识别模型. SFBM有效地减少神经网络中的偏差,提高了代表性不足的阶级的表现.
科学领域:
- 计算机科学 计算机科学
- 人工智能的人工智能
- 机器学习 机器学习
背景情况:
- 现实世界的数据经常表现出长尾分布,其中少数类占主导地位,而大多数只有少数样本.
- 这种不平衡损害了标准识别模型的性能,导致错误分类,特别是尾部类样本.
- 一个关键的问题是神经网络中的共享特征偏差,在神经网络中,多个类的共同特征被错误地优先考虑为头类.
研究的目的:
- 为了解决由长尾分布引起的识别模型的性能下降.
- 提出一种新的框架,即共享特征偏差缓解 (SFBM),以纠正神经网络分类器中的共享特征偏差.
- 在不增加推理复杂性的情况下,提高对尾部类数据的识别模型的准确性.
主要方法:
- 开发了共享特征偏差缓解 (SFBM) 框架.
- 引入了两个并行分类器,与使用专门训练损失的基线分类器同时训练.
- 在使用平行分类器权重的基线分类器权重中估计的共享特征组件.
- 通过删除估计的共享特征并添加特定类别并行分类器权重来纠正基线分类器.
主要成果:
- 该SFBM框架证明了与各种认可方法的广泛兼容性.
- SFBM保持了高的计算效率,在推断过程中没有引入额外的计算.
- 在CIFAR10/100-LT,ImageNet-LT和iNaturalist 2018的实验中,当SFBM在训练期间被纳入时,在最先进的方法中显示出一致的性能提升.
结论:
- 拟议的SFBM框架有效地减轻神经网络分类器中共享特征偏差.
- 在长尾数据集上,SFBM显著提高了识别模型的性能.
- 该框架为不平衡的学习场景提供了一个计算效率高且广泛适用的解决方案.
相关概念视频
01:05Difference from Background: Limit of Detection
7.1K
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...
7.1K
01:19Survival Tree
159
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...
159