均衡损失:长尾物体识别的梯度驱动训练
概括
本研究通过重新平衡不平衡的梯度来解决机器学习中的长尾分布问题. 拟议的均衡损失可以提高各种视觉任务中尾部类别的准确性.
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:
- 长尾分布在现实数据中很普遍,导致代表性不足的类别表现不佳.
- 这种绩效差距主要是由于从积极 (类别内) 和消极 (类别间) 样本的不平衡梯度造成的.
- 累积的正向负梯度的比率表示类别训练平衡.
研究的目的:
- 调查长尾分布中性能降低的原因.
- 开发一种新的梯度驱动训练机制,以解决不平衡的梯度.
- 为改进长尾学习引入一个新的损失函数家族.
主要方法:
- 开发了一种梯度驱动的训练机制,以动态地重新平衡正负梯度.
- 该机制旨在为所有类别实现平衡的梯度比.
- 在这种机制的基础上,引入了一种新的损失函数家族,称为均衡损失.
主要成果:
- 拟议的均衡损失在各种视觉任务中始终超过基线模型.
- 对长尾物体检测 (LVIS),图像分类 (ImageNet-LT,Places-LT, iNaturalist) 和语义细分 (ADE20 K) 进行了实验.
- 该方法在尾部类别的准确度上显示出显著的改进.
结论:
- 拟议的梯度驱动机制通过解决不平衡的梯度,有效地解决了长尾问题.
- 均等损失提供了一种灵活而有效的解决方案,用于改善对代表性不足的数据的模型性能.
- 该方法在多个计算机视觉任务中显示出强大的概括能力.
相关概念视频
01:19Survival Tree
112
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...
112
01:22Force Classification
1.3K
Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
1.3K