人类的注意力引导可解释的人工智能用于计算机视觉模型
Guoyang Liu1, Jindi Zhang2, Antoni B Chan3
1School of Integrated Circuits, Shandong University, Jinan, China; Department of Psychology, University of Hong Kong, Pokfulam Road, Hong Kong.
概括
本研究介绍了以人类注意力为导向的可解释的人工智能 (XAI) 方法,以提高计算机视觉模型的透明度. 这些新技术增强了模型的理解和用户的信任,特别是在对象检测任务中.
科学领域:
- 计算机视觉 计算机视觉
- 人工智能的人工智能
- 人与计算机的交互
背景情况:
- 可解释的人工智能 (XAI) 对于理解黑子AI模型至关重要.
- 开发忠实于模型且对用户可信的XAI方法是一个重大挑战.
- 当前的XAI方法在应用到对象检测任务时,往往缺乏可靠性.
研究的目的:
- 调查将人类注意力知识纳入基于突出性的XAI是否可以提高可信性和可信性.
- 开发由人类注意力引导的对象检测模型的新XAI方法.
- 增强用户的信任和对AI模型决策的理解.
主要方法:
- 开发了FullGrad-CAM和FullGrad-CAM++用于对象检测中的对象特定解释.
- 利用人类的注意力作为解释可信性的客观衡量标准.
- 建议使用可训练的激活功能和光滑内核引导人类注意力的XAI (HAG-XAI).
- 在BDD-100K,MS-COCO和ImageNet数据集上评估方法.
主要成果:
- 新的XAI方法使用人类注意力实现了更高的解释可信性.
- 当前的XAI方法在物体检测中与人类注意力图相比,其忠实性较低.
- 对于物体检测模型,HAG-XAI同时提高了可信度和可信度.
- HAG-XAI提高了用户的信任,并超越了现有的最先进的物体检测XAI方法.
结论:
- 将人类注意力知识嵌入到XAI方法中可以显著提高解释的可信性和可信性.
- HAG-XAI为开发更可靠,更易于理解的人工智能系统提供了一个有希望的方法,特别是在计算机视觉领域.
- 提出的方法在对象检测任务中表现出卓越的性能,推进了可解释AI领域.
更多相关视频
07:09Gaze in Action: Head-mounted Eye Tracking of Children's Dynamic Visual Attention During Naturalistic Behavior
Published on: November 14, 2018
10.6K
08:25Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment
Published on: May 7, 2019
9.0K
相关概念视频
01:20Introduction to Cognitive Psychology
469
Cognitive psychology is the field of psychology dedicated to examining how people think. It attempts to explain how and why we think the way we do by studying the interactions among human thinking, emotion, creativity, language, and problem-solving, as well as other cognitive processes. Cognitive psychology studies how information is processed and manipulated in remembering, thinking, and knowing.
This field emerged in the mid-20th century, following a period dominated by behaviorism, which...
This field emerged in the mid-20th century, following a period dominated by behaviorism, which...
469
01:15Depth Perception and Spatial Vision
631
Depth perception is the ability to perceive objects three-dimensionally. It relies on two types of cues: binocular and monocular. Binocular cues depend on the combination of images from both eyes and how the eyes work together. Since the eyes are in slightly different positions, each eye captures a slightly different image. This disparity between images, known as binocular disparity, helps the brain interpret depth. When the brain compares these images, it determines the distance to an object.
631
01:26Visual System
571
Light enters the eye through the cornea, a transparent, dome-shaped surface covering the surface of the eyeball that helps to direct and focus incoming light. This light is then channeled toward the pupil, an adjustable opening whose size is controlled by the iris. The iris, a pigmented muscle, regulates the amount of light entering the eye by contracting or dilating the pupil, thereby ensuring optimal light levels for clear vision.
Once through the pupil, the light passes through the lens, a...
Once through the pupil, the light passes through the lens, a...
571
01:14Steps in the Modeling Process
200
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...
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...
200