基于类相似度蒸的遥感图像的阶级增量学习
Mingge Shen1,2, Dehu Chen3,4, Silan Hu5
1Zhejiang College of Security Technology, College of Intelligent Equipment, Wenzhou, Zhejiang, China.
PeerJ. Computer science
|October 9, 2023
概括
这项研究引入了一种新的方法,用于在遥感图像中进行类增量物体检测,以减轻灾难性遗忘. 该方法提高了模型的可塑性和稳定性,提高了公共数据集的准确性和培训效率.
科学领域:
- 计算机科学 计算机科学
- 人工智能的人工智能
- 遥感 遥感 遥感 遥感
背景情况:
- 对象检测模型在学习新类时由于数据分布转移而遭受灾难性遗忘.
- 这种忘记阻碍了表现,与人类的学习能力不同.
研究的目的:
- 为远程传感图像开发一个类增量物体检测方法.
- 解决因阶级间分配差异造成的灾难性遗忘问题.
主要方法:
- 引入了类相似性蒸 (CSD) 损失,使用新的和旧的类原型来提高可塑性和稳定性.
- 拟议的全球相似性蒸 (GSD) 损失,以最大限度地提高新旧类特征之间的相互信息.
- 实施基于区域提案网络 (RPN) 的方法,用于准确的标签分配,以防止错误学习.
主要成果:
- 拟议的方法在DOTA和DIOR数据集上的课堂增量学习中实现了更高的准确性.
- 与现有的最先进的方法相比,培训效率显著提高.
- 有效地平衡新类的可塑性和旧类的稳定性.
结论:
- 这种新的方法成功地减轻了在增量物体检测中的灾难性遗忘.
- 为远程传感中不断学习的物体检测模型提供了更强大,更有效的解决方案.
- 在准确性和训练速度方面优于当前的方法,用于类增量学习场景.
相关概念视频
Classification of Systems-II
154
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,
154
Observational Learning
193
Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning...
193
Classification of Systems-I
194
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:
194
Aggregates Classification
332
Aggregate classification is generally based on its size, petrographic characteristics, weight, and source. Size classification ranges from coarse to fine aggregates, defined by the size of the particles. Coarse aggregates are particles that do not pass through ASTM sieve No. 4, and aggregates that pass through the sieve are fine aggregates.
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
332
Introduction to Learning
451
Learning is the process of acquiring knowledge or skills through practice or experience, leading to long-lasting behavioral changes. This acquisition occurs through interaction with the environment and requires practice or experience. For instance, mastering a skill such as surfing requires considerable practice and experience, highlighting the essential role of repeated interactions with the environment in learning.
In contrast to learned behaviors, unlearned behaviors such as crying, sexual...
In contrast to learned behaviors, unlearned behaviors such as crying, sexual...
451
Residuals and Least-Squares Property
7.4K
The vertical distance between the actual value of y and the estimated value of y. In other words, it measures the vertical distance between the actual data point and the predicted point on the line
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...
7.4K


