自主监督的谎言代数表示学习通过最佳法典度量学
IEEE transactions on neural networks and learning systems
|February 8, 2024
概括
本研究介绍了自主监督的李代数网络 (SLA-Net) 用于在有限的数据下进行视觉分类. SLA-Net使用一种新的Lie代数方法,改进了表示学习和概括能力.
科学领域:
- 计算机科学 计算机科学
- 机器学习 机器学习
- 计算机视觉 计算机视觉
背景情况:
- 在有限的训练样本中学习歧视性表示是视觉分类的关键挑战.
- 之前的研究表明,自主监督学习可以提高表现,但Lie组中的正规指标在理论上是有缺陷的.
研究的目的:
- 提出一个理论上可靠的优化测量,用于对李群的表示学习.
- 引入一种新型的自主监督的李代数网络 (SLA-Net),以改善有限数据的视觉分类.
主要方法:
- 证明李代数上的正规度量是有效的优化测量.
- 开发自主监督的李代数网络 (SLA-Net) 框架.
- 在矢量空间中最小化正规度量距离,以避免复杂的多元计算.
- 同时优化自我监督学习和监督分类的参数.
主要成果:
- 证明了在李代数上使用正规度量的理论正确性.
- SLA-Net有效地学习用有限的样本进行视觉分类的表示.
- 通过联合优化实现了改进的概括能力.
结论:
- 拟议的SLA-Net框架提供了一个理论上有效和有效的方法,用于在低数据制度中的表示学习.
- 在视觉分类的八个公共数据集上,SLA-Net的性能优于现有的方法.
- 这项工作推进了自主监督学习技术,用于挑战计算机视觉任务.
相关概念视频
Vector Algebra: Graphical Method
12.1K
Vectors can be multiplied by scalars, added to other vectors, or subtracted from other vectors. The vector sum of two (or more) vectors is called the resultant vector or, for short, the resultant.
We use the laws of geometry to construct resultant vectors, followed by trigonometry to find vector magnitudes and directions. For a geometric construction of the sum of two vectors in a plane, we follow the parallelogram rule. Suppose two vectors are at arbitrary positions. Translate either one of...
We use the laws of geometry to construct resultant vectors, followed by trigonometry to find vector magnitudes and directions. For a geometric construction of the sum of two vectors in a plane, we follow the parallelogram rule. Suppose two vectors are at arbitrary positions. Translate either one of...
12.1K
Vector Algebra: Method of Components
13.9K
It is cumbersome to find the magnitudes of vectors using the parallelogram rule or using the graphical method to perform mathematical operations like addition, subtraction, and multiplication. There are two ways to circumvent this algebraic complexity. One way is to draw the vectors to scale, as in navigation, and read approximate vector lengths and angles (directions) from the graphs. The other way is to use the method of components.
In many applications, the magnitudes and directions of...
In many applications, the magnitudes and directions of...
13.9K
Cartesian Form for Vector Formulation
641
The Cartesian form for vector formulation is a process to calculate the moment of force using the position and force vectors. The moment of force is defined as the cross-product of these vectors, making it a vector quantity. The Cartesian form of the position and force vectors involves unit vectors, which can be used to express the cross-product in determinant form.
641
Cartesian Vector Notation
774
Cartesian vector notation is a valuable tool in mechanical engineering for representing vectors in three-dimensional space, performing vector operations such as determining the gradient, divergence, and curl, and expressing physical quantities such as the displacement, velocity, acceleration, and force. By using Cartesian vector notation, engineers can more easily analyze and solve problems in various areas of mechanical engineering, including dynamics, kinematics, and fluid mechanics. This...
774
Associative Learning
362
Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
Classical conditioning, also known...
362
State Space Representation
208
The frequency-domain technique, commonly used in analyzing and designing feedback control systems, is effective for linear, time-invariant systems. However, it falls short when dealing with nonlinear, time-varying, and multiple-input multiple-output systems. The time-domain or state-space approach addresses these limitations by utilizing state variables to construct simultaneous, first-order differential equations, known as state equations, for an nth-order system.
Consider an RLC circuit, a...
Consider an RLC circuit, a...
208


