什么使得等级视觉变压器?
IEEE transactions on pattern analysis and machine intelligence
|October 11, 2023
概括
层次视觉转换器 (ViT) 可以使用新的宏观架构实现最高性能. 在ViT中用线性层取代自我注意力表明了强大的图像识别和转移学习能力.
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:
- 以窗口为基础的自我注意的层次视觉转换器 (ViT) 实现了最先进的结果,挑战了卷积神经网络 (CNN).
- 目前,自我注意是层次ViT中的空间信息聚合的标准.
研究的目的:
- 为了调查是否自我注意力是必要的,在等级ViTs高绩效.
- 探索不同交叉窗口通信方法的影响.
- 评估空间信息聚合的替代方法.
主要方法:
- 用线性映射层取代自我注意层,以创建跨线性架构.
- 在ImageNet-1K图像识别上评估了TransLinear.
- 评估下游任务的转移学习能力,如对象检测和实例细分.
- 实验了替代内容聚合层和交叉窗口通信策略.
主要成果:
- 在ImageNet-1K图像识别上,TransLinear架构实现了强的性能.
- 在下游密集的预测任务中,TransLinear展示了具有竞争力的转移学习特性.
- 该研究发现,宏观架构,而不是特定的聚合层或通信机制,是层次 ViTs 的性能的主要驱动因素.
结论:
- 层次ViT的宏观架构是其强性能的关键因素,不一定是自我注意.
- 简单的线性层可以有效地取代ViT中的自我注意力,提供具有竞争力的结果.
- 这些发现表明,ViTs的宏观架构对传统的CNN范式构成了重大挑战.
相关概念视频
01:24Vision
Vision is the result of light being detected and transduced into neural signals by the retina of the eye. This information is then further analyzed and interpreted by the brain. First, light enters the front of the eye and is focused by the cornea and lens onto the retina—a thin sheet of neural tissue lining the back of the eye. Because of refraction through the convex lens of the eye, images are projected onto the retina upside-down and reversed.
01:26Transformers
A device that transforms voltages from one value to another using induction is called a transformer. A transformer consists of two separate coils, or windings, wrapped around the same soft iron core. However, they are electrically insulated from each other.
The iron core has a substantial relative permeability. Therefore, the magnetic field lines generated due to the current in one winding are almost entirely confined within the core, such that the same magnetic flux permeates each turn of both...
The iron core has a substantial relative permeability. Therefore, the magnetic field lines generated due to the current in one winding are almost entirely confined within the core, such that the same magnetic flux permeates each turn of both...
01:16Types Of Transformers
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...
01:27Transformers in Distribution System
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...
01:19Three-Winding Transformers
Three identical single-phase transformers can be configured to form a three-phase transformer connection, which involves high-voltage and low-voltage windings. The high-voltage windings are denoted by capital letters A-B-C, while the low-voltage windings are labeled with lowercase letters a-b-c, representing their respective phases. This notation helps distinguish between the high and low voltage sides of the transformer.
In the per-unit equivalent circuit of a grounded Y-Y three-phase...
In the per-unit equivalent circuit of a grounded Y-Y three-phase...
01:25Transformers with Off-Nominal Turns Ratios
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 rated...