使用图纸和深度神经网络来描述人类视觉相似性的构建块
Kushin Mukherjee1, Timothy T Rogers2
1Department of Psychology & Wisconsin Institute for Discovery, University of Wisconsin-Madison, Madison, WI, USA. kmukherjee2@wisc.edu.
Memory & cognition
|May 30, 2024
概括
人类的视觉感知依赖于抽象视觉相似之处. 深度神经网络 (DNN) 在模拟这一点方面表现有前途,特别是视觉转换器处理图像和文本.
科学领域:
- 认知科学 认知科学
- 计算机视觉 计算机视觉
- 神经科学是一个神经科学.
背景情况:
- 人类自然地感知到抽象表示和现实世界对象之间的视觉相似性.
- 深度神经网络 (DNN) 越来越多地用于模拟人类的视觉感知.
研究的目的:
- 评估不同DNN如何解释人类对视觉刺激的相似性判断.
- 调查语义信息与视觉特征在感知相似性的作用.
主要方法:
- 对比了五个当代DNN在预测人类相似性判断线条图的能力.
- 分析了对人类判断的DNN表示,用于可识别和新的对象草图.
- 使用视觉转换器训练图像和文本数据.
主要成果:
- 对对象草图的人类相似性判断主要是由语义类别驱动的,DNN提供了很少的额外洞察力.
- DNN特征解释了对抽象图纸的感知相似性的显著差异.
- 一个整合图像和自然语言描述的视觉转换器最好地解释了人类的感知相似性.
结论:
- 视觉相似性的构建块可能来自于优先考虑语义表示而不是特定分类任务的系统.
- 视觉转换器显示出作为人类语义表示和处理模型的潜力.
- DNN可以成为了解人类视觉感知机制的宝贵工具.
相关概念视频
01:12Modeling and Similitude
262
Scaled modeling is a fundamental technique in engineering, enabling the study of large and complex systems by creating smaller, manageable replicas that recreate critical characteristics of the original. In hydrology and civil infrastructure, for example, scaled models of dams help analyze water flow, turbulence, and pressure. This method allows for accurate predictions of real-world behavior within a controlled environment, significantly reducing the cost and time involved in full-scale...
262
01:26Visual System
570
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...
570