在现代图像深度网络中解密变压器和卷积.
概括
视觉变压器受益于先进的架构,而不仅仅是功能设计. 本研究将空间令牌混合器 (STM) 确定为关键差异化因素,揭示了它们对性能和稳定性的影响.
科学领域:
- 计算机视觉 计算机视觉
- 机器学习 机器学习
- 人工智能的人工智能
背景情况:
- 视觉转换器 (ViT) 已经成为计算机视觉的强大支柱,提供了性能改进.
- 在ViT的进步归因于新的功能转换设计和复杂的网络/块架构.
研究的目的:
- 隔离和量化视觉变压器中使用的不同空间令牌混合器 (STM) 的性能增长.
- 通过中和架构变异来提供卷积和注意力运算符的公平比较.
主要方法:
- 引入了一个统一的架构来标准化网络和块级设计.
- 在这个统一的框架内集成和评估了各种空间令牌混合器 (STM).
- 在各种任务中进行了实验,并分析了诱导偏见.
主要成果:
- 先进的网络和块级设计显著提高了性能.
- 在各种STM中观察到明显的性能差异.
- 分析揭示了对STM有效受体场,不变性属性和对抗性强度的见解.
结论:
- 空间令牌混合器 (STM) 对视觉变压器的性能至关重要,变化会影响结果.
- 网络和区块级别的架构选择在整体性能增长中发挥着重要作用.
- 该研究为了解和优化视觉变压器设计中的STM提供了一个框架.
相关概念视频
Types Of Transformers
943
Transformers can provide desired voltages to a circuit by modifying the number of turns in the secondary windings.
If the ratio of the number of turns in the secondary winding to that of the primary winding is greater than one, then the transformer is said to be a step-up transformer. In a step-up transformer, the voltage at the secondary winding is greater than the voltage applied at the primary winding.
However, if this ratio is less than one, the transformer is said to be a step-down...
If the ratio of the number of turns in the secondary winding to that of the primary winding is greater than one, then the transformer is said to be a step-up transformer. In a step-up transformer, the voltage at the secondary winding is greater than the voltage applied at the primary winding.
However, if this ratio is less than one, the transformer is said to be a step-down...
943
Convolution: Math, Graphics, and Discrete Signals
223
In any LTI (Linear Time-Invariant) system, the convolution of two signals is denoted using a convolution operator, assuming all initial conditions are zero. The convolution integral can be divided into two parts: the zero-input or natural response and the zero-state or forced response, with t0 indicating the initial time.
To simplify the convolution integral, it is assumed that both the input signal and impulse response are zero for negative time values. The graphical convolution process...
To simplify the convolution integral, it is assumed that both the input signal and impulse response are zero for negative time values. The graphical convolution process...
223
Transformers in Distribution System
98
Transformers in distribution systems can be broadly categorized into distribution substation transformers and other distribution transformers. They are crucial for stepping down high transmission voltages to levels suitable for distribution and end-user applications.
Distribution substation transformers come in various ratings and typically use mineral oil for insulation and cooling. To prevent moisture and air from entering the oil, some transformers use an inert gas like nitrogen to fill the...
Distribution substation transformers come in various ratings and typically use mineral oil for insulation and cooling. To prevent moisture and air from entering the oil, some transformers use an inert gas like nitrogen to fill the...
98
Convolution Properties I
131
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:
131
Convolution Properties II
166
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...
166
Transformers with Off-Nominal Turns Ratios
129
In scenarios involving parallel transformers with disparate ratings, developing per-unit models requires accommodating off-nominal turns ratios. This situation arises when the selected base voltages are not proportional to the transformer’s voltage ratings. Consider a transformer where the rated voltages are related by the term a. If the chosen voltage bases satisfy a relationship involving term b, term c is defined as the ratio of these bases. This ratio is then substituted into the...
129


