人类眼睛启发的循环神经网络对抗敌对噪音更为坚固
Minkyu Choi1, Yizhen Zhang2, Kuan Han3
1Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI 48105, U.S.A. cminkyu@umich.edu.
Neural computation
|August 6, 2024
概括
这项研究引入了一种模仿人类注意力的双流视觉模型,以改进图像识别. 该模型使用顺序固定,增强对抗攻击的稳定性,并通过反复处理实现错误校正.
科学领域:
- 计算机视觉 计算机视觉
- 神经科学是一个神经科学.
- 人工智能的人工智能
背景情况:
- 卷积神经网络 (CNN) 通常在一次通过中处理视觉数据.
- 人类的视觉系统专注于突出的物体,忽略不相关的细节.
- 当前的计算机视觉模型缺乏类似人类的注意力机制.
研究的目的:
- 设计一种由人类大脑启发的双流视觉模型.
- 通过固定来实现连续的图像处理.
- 为了提高对象识别和对抗强度.
主要方法:
- 开发了一个带有视网膜类输入层的双流模型.
- 一个流确定固定点;另一个流解释周围的视觉效果.
- 在图像识别任务上训练模型,并在基准上评估性能.
主要成果:
- 该模型在没有明确的训练的情况下展示了类似人类的注意力和凝视行为.
- 视网膜采样和反复处理增强了对抗攻击的稳定性.
- 该模型通过多次目光重新检查图像部分来纠正感知错误.
结论:
- 视网膜采样,眼睛运动和反复的动态对于类似人类的视觉探索至关重要.
- 双流模型为计算机视觉提供了一种新的方法,超越了仅供给前模型.
- 这种生物启发的模型推进了对视觉推断和注意力的理解.
相关概念视频
01:20Anatomy of the Eyeball
6.8K
The eye is a spherical, hollow structure composed of three tissue layers. The outer layer — the fibrous tunic, comprises the sclera — a white structure — and the cornea, which is transparent. The sclera encompasses some of the ocular surface, most of which is not visible. However, the 'white of the eye' is distinctively visible in humans compared to other species. The cornea, a clear covering at the front of the eye, enables light penetration. The eye's middle...
6.8K
01:24Vision
53.1K
Vision is the result of light being detected and transduced into neural signals by the retina of the eye. This information is then further analyzed and interpreted by the brain. First, light enters the front of the eye and is focused by the cornea and lens onto the retina—a thin sheet of neural tissue lining the back of the eye. Because of refraction through the convex lens of the eye, images are projected onto the retina upside-down and reversed.
53.1K