李群卷积神经网络具有尺度旋转等差
Weidong Qiao1, Yang Xu2, Hui Li3
1Key Lab of Smart Prevention and Mitigation of Civil Engineering Disasters of the Ministry of Industry and Information Technology, Harbin Institute of Technology, Harbin 150090, China.
概括
这项研究引入了一种新的SIM(2) 谎言组-CNN,增强卷积神经网络 (CNN) 具有同时缩放,旋转和翻译等价性,用于优越的图像分类. 这种方法有效地提取几何特征,提高了转换图像的识别精度.
科学领域:
- 计算机视觉 计算机视觉
- 深度学习 (Deep Learning) 是一种深度学习.
- 几何深度学习 几何深度学习
背景情况:
- 卷积神经网络 (CNN) 由于重量共享而表现出翻译等价性.
- 现有的CNN缺乏与尺度和旋转转变的固有等价性.
- 处理几何变化对于强大的图像分类至关重要.
研究的目的:
- 提出一个SIM(2) 谎言组-CNN用于同时缩放,旋转和转换等价值.
- 为了在几何变换下实现强大的图像分类.
- 为了解决SIM上的度量定义(2) 谎组空间.
主要方法:
- 一个提升模块将输入图像从欧几里德空间映射到Lie组空间.
- 组卷积模块使用李代数系数进行参数化,用于尺度和旋转等差.
- 一个完全连接的网络和全球聚合层促进了分类.
主要成果:
- SIM(2) 谎言组-CNN 证明了经过验证的尺度旋转等差.
- 在具有旋转和尺度变化的图像数据集上实现了最先进的识别精度.
- 从转换的图像中成功提取了几何特征.
结论:
- 拟议的SIM(2) 谎组-CNN有效地处理尺度,旋转和转换等差.
- 这种方法为等价图像识别提供了一个强大的框架.
- 对SIM的明确定义(2) 度量推进了几何深度学习研究.
相关概念视频
Vector Transformation in Rotating Coordinate Systems
1.5K
Consider a vector rotating about an axis with an angular velocity, such that its tip sweeps a circular path.
1.5K
Sequence Networks of Rotating Machines
96
A Y-connected synchronous generator, grounded through a neutral impedance, is designed to produce balanced internal phase voltages with only positive-sequence components. The generator's sequence networks include a source voltage that is exclusively in the positive-sequence network. The sequence components of line-to-ground voltages at the generator terminals illustrate this configuration.
Zero-sequence current induces a voltage drop across the generator's neutral impedance and other...
Zero-sequence current induces a voltage drop across the generator's neutral impedance and other...
96
Convolution Properties II
173
The important convolution properties include width, area, differentiation, and integration properties.
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
173
Convolution Properties I
137
Convolution computations can be simplified by utilizing their inherent properties.
The commutative property reveals that the input and the impulse response of an LTI (Linear Time-Invariant) system can be interchanged without affecting the output:
The commutative property reveals that the input and the impulse response of an LTI (Linear Time-Invariant) system can be interchanged without affecting the output:
137
Gauss's Law: Cylindrical Symmetry
7.4K
A charge distribution has cylindrical symmetry if the charge density depends only upon the distance from the axis of the cylinder and does not vary along the axis or with the direction about the axis. In other words, if a system varies if it is rotated around the axis or shifted along the axis, it does not have cylindrical symmetry. In real systems, we do not have infinite cylinders; however, if the cylindrical object is considerably longer than the radius from it that we are interested in,...
7.4K
Scaling
228
In designing and analyzing filters, resonant circuits, or circuit analysis at large, working with standard element values like 1 ohm, 1 henry, or 1 farad can be convenient before scaling these values to more realistic figures. This approach is widely utilized by not employing realistic element values in numerous examples and problems; it simplifies mastering circuit analysis through convenient component values. The complexity of calculations is thereby reduced, with the understanding that...
228


