以课程为指导的对抗性学习,以提高3D对象检测中的稳定性
Jinzhe Huang1, Yiyuan Xie2, Zhuang Chen2
1College of Computer and Information Science, Chongqing Normal University, Chongqing 401331, China.
Sensors (Basel, Switzerland)
|April 28, 2025
概括
本研究引入了课程引导的对抗性学习 (CGAL) 框架,以改善3D对象检测. 该方法增强了对新型攻击的稳定性,并提高了基于LiDAR的系统的检测精度.
科学领域:
- 计算机视觉 计算机视觉
- 机器学习 机器学习
- 机器人技术 机器人技术 机器人技术
背景情况:
- 对于自主系统来说,3D对象检测至关重要.
- 像PointPillars这样的基于LiDAR的探测器面临着对抗性强度和阶级不平衡的挑战.
- 现有的方法往往缺乏对复杂攻击的固有弹性.
研究的目的:
- 开发一个框架,增强基于LiDAR的3D物体探测器的对抗性稳定性和检测精度.
- 推出一种具有内在对抗性强度的新型3D物体探测器.
- 为了解决3D对象检测数据集中的类不平衡问题.
主要方法:
- 提出了一个课程指导的对抗性学习 (CGAL) 框架.
- 开发了一种新的3D物体探测器Pillar-RBFN,将非线性增强块 (NEB) 与辐射基函数网络集成在一起.
- 引入了数据增强技术 (SFGTS) 和适应焦点损失,以创建对抗数据集 (Adv-KITTI) 并减轻类失衡.
主要成果:
- 与传统培训相比,CGAL框架提高了0.82.5个百分点的平均平均精度 (mAP).
- 用Adv-KITTI训练的模型显示至少15个百分点的mAP增强.
- 支柱-RBFN在没有对抗训练的情况下展示了内在的对抗稳定性.
结论:
- 拟议的CGAL框架显著提高了基于LiDAR的3D物体检测的对抗性稳定性和检测精度.
- 新的Pillar-RBFN探测器提供了对敌对攻击的固有弹性.
- 开发的数据增量和丢失功能有效地解决了类不平衡问题,改善了整体模型性能.
更多相关视频
03:31Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
Published on: December 15, 2023
428
06:20Author Spotlight: Development of an Automated Camera-Based System for Real-Time Blast Overpressure Monitoring and TBI Risk Assessment in Military Training
Published on: December 6, 2024
2.3K
相关概念视频
01:12Observational Learning
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 because...
01:25Maximizing the Directional Derivative
The directional derivative is a central concept in multivariable calculus that describes how a function changes at a given point when moving in a specified direction. This direction is represented by a unit vector, ensuring that only the orientation influences the rate of change. By varying the direction, different rates of change can be observed, demonstrating that the directional derivative depends strongly on the chosen direction.The directional derivative is computed using the gradient...