InfoCAM:一种信息加权的类激活映射,用于解释视觉神经网络
Yulong Shi1, Mingwei Sun1, Zengqiang Chen2
1College of Artificial Intelligence, Nankai University, Tianjin, 300350, China.
概括
研究人员开发了信息加权类激活映射 (InfoCAM),以提高深度视觉神经网络的透明度. 这种新的框架通过分解特征激活来提供可靠的视觉解释,从而提高了模型的可解释性.
科学领域:
- 计算机视觉 计算机视觉
- 人工智能的人工智能
- 深度学习 (Deep Learning) 是一种深度学习.
背景情况:
- 深度学习模型,特别是视觉神经网络,由于复杂的非线性函数和超参数调整而表现出黑子行为.
- 缺乏透明度阻碍了对视觉神经网络中的决策过程的理解.
研究的目的:
- 提高深度视觉神经网络的透明度和可解释性.
- 提出一个突出视觉解释框架,提供可靠的解释.
主要方法:
- 拟议的信息加权类激活映射 (InfoCAM),一个新的突出性视觉解释框架.
- 引入了一个双流信息瓶 (DSIB) 模块,使用变异推理将特征激活分解为歧视性和噪声流.
- 优化了区分流和输出预测之间的相互信息,为激活地图赋予忠实权重.
主要成果:
- 通过忠实地将权重分配给功能激活地图,InfoCAM产生可靠的视觉解释.
- 该框架能够应对破碎梯度问题,并与各种网络架构和任务无集成.
- 通过澄清理论界限和降低对输出得分波动的敏感性,改进了忠实度评估指标 (平均下降和平均上升).
结论:
- InfoCAM为视觉神经网络提供了可靠的解释方法,提高了透明度.
- 在干扰测试和基于能量的指针游戏评估中表现出卓越的表现.
- 在创建可解释的计算机视觉深度学习模型方面,InfoCAM提供了显著的进步.
相关概念视频
Neural Circuits
3.0K
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
3.0K
Vision
60.8K
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.
60.8K
