奇美拉:一个基于块的神经架构搜索框架,用于基于事件的对象检测
Diego A Silva1, Ahmed Elsheikh2, Kamilya Smagulova1
1Communication and Computing Systems Lab, Computer, Electrical and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia.
Frontiers in artificial intelligence
|October 17, 2025
概括
基于事件的对象检测的新框架 Chimera 增强了事件摄像头数据的处理. 这种方法实现了最先进的结果,提高了效率,优于现有方法.
科学领域:
- 计算机视觉 计算机视觉
- 神经形态工程的神经形态工程
背景情况:
- 基于事件的摄像头模仿人眼,提供高速和低功耗的优势.
- 深度学习有效地处理事件数据,但优化潜力仍然存在.
- 将RGB域技术适应事件数据需要专门的框架.
研究的目的:
- 介绍Chimera,一个基于区块的神经架构搜索 (NAS) 框架.
- 系统地适应RGB域处理方法以基于事件的对象检测.
- 探索宏观区块组合,以优化本地和全球处理.
主要方法:
- 开发了Chimera,这是一个基于事件的对象检测NAS框架.
- 使用宏观块设计了一个搜索空间:注意力,卷积,状态空间模型,MLP混合器.
- 根据Prophesee GEN1数据集进行评估.
主要成果:
- 实现了基于事件的对象检测的最先进的平均精度 (mAP).
- 与现有方法相比,模型参数减少了1.6倍.
- 在处理过程中表现出2.1倍的加快速度.
结论:
- 奇美拉提供了一种系统的方法来优化基于事件视觉的深度学习.
- 该框架在处理能力和复杂性之间提供了灵活的权衡.
- 结果表明,基于事件的对象检测效率和性能取得了显著的进步.
相关概念视频
Elastic Collisions: Introduction
An elastic collision is one that conserves both internal kinetic energy and momentum. Internal kinetic energy is the sum of the kinetic energies of the objects in a system. Truly elastic collisions can only be achieved with subatomic particles, such as electrons striking nuclei. Macroscopic collisions can be very nearly, but not quite, elastic, as some kinetic energy is always converted into other forms of energy such as heat transfer due to friction and sound. An example of a nearly...
Elastic Collisions: Case Study
Elastic collision of a system demands conservation of both momentum and kinetic energy. To solve problems involving one-dimensional elastic collisions between two objects, the equations for conservation of momentum and conservation of internal kinetic energy can be used. For the two objects, the sum of momentum before the collision equals the total momentum after the collision. An elastic collision conserves internal kinetic energy, and so the sum of kinetic energies before the collision equals...

