相关实验视频

Updated: Jun 4, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

反对训练和归因方法可以评估图像分类深度学习模型的稳定性和可解释性

Flávio A O Santos¹, Cleber Zanchettin^1,2, Weihua Lei³

¹Centro de Informática, <a href="https://ror.org/047908t24">Universidade Federal de Pernambuco</a>, Recife, Pernambuco, 52061080, Brazil.

Physical review. E

|December 18, 2024

概括

反对训练显著改变了深度学习模型的可解释性,使预测更强大. 这项研究对输入归因方法进行了基准测试,揭示了可靠的人工智能可靠的方法.

科学领域:

人工智能的人工智能
计算机视觉计算机视觉
机器学习机器学习

背景情况:

深度学习模型优秀,但对对抗性攻击和分布外数据表现出脆弱性.
模型的可解释性对于理解和解决这种脆弱性至关重要.

研究的目的:

调查对抗性培训对输入归因方法的影响.
对深度学习模型进行基准测试并确定可靠的输入归因技术.

主要方法:

图像分类的组合对抗和输入归因方法.
评估了输入归因的信号噪声比,并与模型信心相关联.

主要成果:

与标准方法相比,对抗性训练产生了不同的输入归因矩阵.
确定可靠的输入归因方法和确认的对抗训练提高了预测的稳定性.

结论:

反对训练提高了深度学习模型的稳定性和可解释性.
拟议的方法提高了对深度学习模型可靠性的信心,并可扩展到其他领域.

更多相关视频

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

相关概念视频

Fundamental Attribution Error

Fundamental Attribution Error

According to some social psychologists, people tend to overemphasize internal factors as explanations—or attributions—for the behavior of other people. They tend to assume that the behavior of another person is a trait of that person, and to underestimate the power of the situation on the behavior of others. They tend to fail to recognize when the behavior of another is due to situational variables, and thus to the person’s state. This erroneous assumption is...

Steps in the Modeling Process

Steps in the Modeling Process

Albert Bandura's theory of observational learning identifies four critical processes: attention, retention, motor reproduction, and reinforcement or motivation.
Attention is the first necessary component for observational learning. It involves focusing on what the model is doing and saying. For example, if you decide to take a drawing class to enhance your skills, you need to pay close attention to the instructor's words and hand movements. The characteristics of the model significantly...