重新审视几拍图像分类的可转移性:一个频谱视角
Min Zhang1,2, Zhitao Wang2, Donglin Wang2
1College of Computer Science & Technology, Zhejiang University, Hangzhou 310027, China.
Entropy (Basel, Switzerland)
|June 26, 2024
概括
本研究通过分析频谱来研究少数拍摄图像分类 (FSIC). 开发了一种新的频域调节和选择方法 (FRSM),通过减轻非因果频率影响来提高模型的可转移性.
科学领域:
- 计算机科学 计算机科学
- 人工智能的人工智能
- 机器学习 机器学习
背景情况:
- 短拍图像分类 (FSIC) 旨在通过利用基础类别的知识来对具有有限数据的新类别进行分类.
- 现有的FSIC方法由于基础类和新型类之间的分配转移而存在缺陷的可转移性.
- 业绩下降的根本原因以及FSIC中转移信息的性质仍在争论中.
研究的目的:
- 阐明FSIC业绩下降的原因.
- 为了确定FSIC测试期间传递的特定信息.
- 提出一种新的方法来提高FSIC的可转移性.
主要方法:
- 该研究采用了基于FSIC频率领域的因果关系方法.
- 非因果频率 (例如背景) 被确定为影响预测的混因素.
- 建议使用频域调节和选择方法 (FRSM) 来权衡频率并减少非因果因素的影响.
主要成果:
- 图像中的不同频率组件对应于不同的语义信息.
- 非因果频率会对FSIC模型的可转移性产生负面影响,导致性能低于最佳.
- 拟议的FRSM方法显著提高FSIC模型的可转移性.
结论:
- 了解频率组件的作用对于改善FSIC至关重要.
- 减轻非因果频率的影响可以提高模型的概括性.
- FRSM方法提供了一种简单而有效的解决方案,用于在各种数据集中提高FSIC的性能.
相关概念视频
Classification of Signals
435
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...
435
Aliasing
128
Accurate signal sampling and reconstruction are crucial in various signal-processing applications. A time-domain signal's spectrum can be revealed using its Fourier transform. When this signal is sampled at a specific frequency, it results in multiple scaled replicas of the original spectrum in the frequency domain. The spacing of these replicas is determined by the sampling frequency.
If the sampling frequency is below the Nyquist rate, these replicas overlap, preventing the original...
If the sampling frequency is below the Nyquist rate, these replicas overlap, preventing the original...
128
Properties of Fourier Transform II
200
The Fourier Transform (FT) is an essential mathematical tool in signal processing, transforming a time-domain signal into its frequency-domain representation. This transformation elucidates the relationship between time and frequency domains through several properties, each revealing unique aspects of signal behavior.
The Frequency Shifting property of Fourier Transforms highlights that a shift in the frequency domain corresponds to a phase shift in the time domain. Mathematically, if x(t) has...
The Frequency Shifting property of Fourier Transforms highlights that a shift in the frequency domain corresponds to a phase shift in the time domain. Mathematically, if x(t) has...
200
Linear Approximation in Frequency Domain
89
Linear systems are characterized by two main properties: superposition and homogeneity. Superposition allows the response to multiple inputs to be the sum of the responses to each individual input. Homogeneity ensures that scaling an input by a scalar results in the response being scaled by the same scalar.
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
89
Force Classification
1.2K
Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
1.2K
Bandpass Sampling
171
In signal processing, bandpass sampling is an effective technique for sampling signals that have most of their energy concentrated within a narrow frequency band. This type of signal is known as a bandpass signal. The key principle of bandpass sampling involves sampling the signal at a rate that is greater than twice the signal's bandwidth to prevent aliasing.
A bandpass signal has a spectrum with a lower frequency limit, denoted as ω1, and an upper frequency limit, denoted as ω2....
A bandpass signal has a spectrum with a lower frequency limit, denoted as ω1, and an upper frequency limit, denoted as ω2....
171


