什么使一个场景类别的好例子好? 来自深层神经网络的证据
1Department of Psychology, University of Illinois Urbana-Champaign, United States.
Vision research
|November 14, 2025
概括
好的示例,或具有高度代表性的图像,比不好的示例包含更多的类别信息. 深度神经网络 (DNN) 可以捕捉到这种人类代表性,有助于理解场景类别.
科学领域:
- 认知科学 认知科学
- 计算机视觉 计算机视觉
- 机器学习 机器学习
背景情况:
- 代表性影响一个样本如何定义其类别.
- 了解模范信息性是有效的机器学习和人类认知研究的关键.
研究的目的:
- 调查是否高度代表性 (好的) 场景类别的示例比不太代表性 (坏的) 有更多的信息.
- 确定深度神经网络 (DNN) 是否能够捕捉人类对代表性和类别信息性的判断.
主要方法:
- 利用各种深度神经网络 (像AlexNet,PlaceNet,ResNet这样的CNN;像ViT,CLIP这样的变压器) 来从自然场景图像中提取特征.
- 使用一次性支持矢量机 (SVM) 分类器来评估基于每类单个样本的分类准确性.
- 从DNN特征和人类相似性判断得出的分析类别空间.
主要成果:
- 在所有测试的特征上,良好的样本总是比不良的样本产生更高的分类准确性.
- 需要多个糟糕的样本来匹配一个好的样本中包含的类别信息.
- 高度信息化的图像和好的范例通常位于类别空间的边缘,而不是中心.
结论:
- 深度神经网络有效地捕捉了人类对自然场景类别的代表性判断.
- 一个示例的信息性与其在一个类别中的代表性直接相关.
- DNN为量化代表性和绘制人类场景类别空间提供了有价值的工具.
相关概念视频
Neural Circuits
2.6K
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...
2.6K
Observational Learning
804
Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning...
804
Classification of Signals
1.3K
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
1.3K
