通过低级别的双线组合来学习紧的差异化表示
IEEE transactions on pattern analysis and machine intelligence
|August 21, 2025
概括
这项研究引入了一种新方法,通过使用主要组件分析 (PCA) 来减少双线聚合的过度配合. 拟议的rank-k正交因子双线聚合 (RK-OFBP) 实现了具有明显较低特征尺寸的竞争性分类结果.
科学领域:
- 计算机科学
- 机器学习
- 计算机视觉
背景情况:
- 双线聚合会产生差异性特征,但具有很高的维度和差异性,导致过度匹配.
- 主要组件分析 (PCA) 是一种可以应用于双线特征的维度减小技术.
- 现有的因子化双线组合方法可能无法最佳地保持特征的可区分性.
研究的目的:
- 通过减少特征维度和差异来解决双线聚合的过度匹配问题.
- 开发一种基于数学的方法来减少双线特征的尺寸.
- 提出一种新的双线聚合方法,在计算上是高效和有效的.
主要方法:
- 构建了一个双层优化问题,结合了分类损失和PCA.
- 已证明的双线性特征的PCA相当于光谱聚类,为维度缩小设定下限.
- 建议使用k级一般双线投影 (RK-GBP) 来分解PCA投影矩阵.
- 通过将PCA放松到字典学习以提高效率,开发了k级直角因子双线聚合 (RK-OFBP).
主要成果:
- 数学证明第一个log2 ((C) 主要组件捕获了C类的区分信息.
- 证明RK-OFBP同时减少双线特征的维度和变异.
- 使用显著较低的维度特征 (例如32维向量) 实现了与现有方法 (例如B-CNN) 相比的分类性能.
结论:
- 拟议的RK-OFBP方法通过原则性的尺寸缩小有效地减轻了双线聚合的过度拟合.
- RK-OFBP提供了一种通用和高效的因子化双线聚合方法,在细粒度和大规模数据集上表现优于以前的方法.
- 这项工作为双线聚合的尺寸缩小提供了第一个理论下限,并提供了高性能的实践实施.
相关概念视频
01:20Downsampling
252
When considering a sampled sequence with zero values between sampling instants, one can replace it by taking every N-th value of the sequence. At these integer multiples of N, the original and sampled sequences coincide. This process, known as decimation, involves extracting every N-th sample from a sequence, thereby creating a more efficient sequence.
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...
252
01:14Extraction: Partition and Distribution Coefficients
2.9K
The distribution law or Nernst's distribution law is the law that governs the distribution of a solute between two immiscible solvents. This law, also known as the partition law, states that if a solute is added to the mixture of two immiscible solvents at a constant temperature, the solute is distributed between the two solvents in such a way that the ratio of solute concentrations in the solvents remains constant at equilibrium.
For extracting a solute from an aqueous phase into an...
For extracting a solute from an aqueous phase into an...
2.9K
01:11Residuals and Least-Squares Property
7.8K
The vertical distance between the actual value of y and the estimated value of y. In other words, it measures the vertical distance between the actual data point and the predicted point on the line
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...
7.8K
01:26Linear Approximation in Frequency Domain
131
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....
131
01:19Routh-Hurwitz Criterion II
402
In the application of the Routh-Hurwitz criterion, two specific scenarios can arise that complicate stability analysis.
The first scenario occurs when a singular zero appears in the first column of the Routh table. This situation creates a division by zero issues. To resolve this, a small positive or negative number, denoted as epsilon (∈), is substituted for the zero. The stability analysis proceeds by assuming a sign for ∈. If ∈ is positive, any sign change in the first...
The first scenario occurs when a singular zero appears in the first column of the Routh table. This situation creates a division by zero issues. To resolve this, a small positive or negative number, denoted as epsilon (∈), is substituted for the zero. The stability analysis proceeds by assuming a sign for ∈. If ∈ is positive, any sign change in the first...
402
01:20Deconvolution
251
Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
251