MViT: 一个视觉变换器,具有碎形路径重新排序和动态位置编码.
Bomin Liu1, Linjun He1, Yan Zhu1
1School of Design and Art, Shanghai Dianji University, Shanghai, China.
PloS one
|January 16, 2026
概括
摩尔曲线视觉转换器 (MViT) 通过提高空间连续性和适应性来增强图像分析. 这种新的框架为分类任务提供了更好的性能和图像旋转的稳定性.
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) 在图像任务中表现出色,但由于固定的分区和静态位置编码,由于空间连续性而扎.
- 限制包括难以表示旋转结构和不规则边界,阻碍复杂图像布局的性能.
研究的目的:
- 引入摩尔曲线视觉转换器 (MViT),这是一个新的ViT框架,旨在克服空间连续性的限制.
- 在图像分析中增强旋转结构和不规则边界的表示.
主要方法:
- MViT框架使用递归的摩尔曲线,结合多顺序的碎形映射,以优化补丁重新排序和增强空间连贯性.
- 动态分区模板和边界补偿算法改善了密集的结构表示和分辨率适应性.
- 一个周期感知定位编码模块将嵌入式与碎形穿越模式对齐,整合碎形参数和卷积特征.
主要成果:
- 与ViT-B/16相比,MViT在CIFAR-100上提高了0.52%的分类精度,在ImageNet-21k上提高了0.31%的分类精度.
- 在峰值信号与噪声比率 (PSNR) 和结构相似度指数 (SSIM) 中观察到明显的改善.
- 实验证实了MViT对旋转和局部焦点变化的稳定性,证明了在不同骨干和任务之间强大的结构兼容性.
结论:
- MViT框架显著提高了复杂图像布局的结构适应性.
- MViT提供了更好的性能和稳定性,使其成为各种计算机视觉应用的多功能工具.
相关概念视频
Transformers with Off-Nominal Turns Ratios
523
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...
523
Transformers in Distribution System
498
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...
498
Types Of Transformers
1.4K
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...
1.4K
Position and Displacement Vectors
12.6K
To describe the motion of an object, one should first be able to describe its position (where it is at any particular time). More precisely, the position needs to be specified relative to a convenient frame of reference. A frame of reference is an arbitrary set of axes from which the position and motion of an object are described. Earth is often used as a frame of reference to describe the position of an object in relation to stationary objects on Earth.
Further, several important kinds of...
Further, several important kinds of...
12.6K
Transformation
709
Microbial communities are dynamic environments where cell lysis releases free DNA into the surroundings. Other cells can take up this extracellular DNA through a process known as transformation.When a cell incorporates this foreign DNA into its genome, resulting in genetic modification, the process is known as transformation. Cells capable of this process are termed competent. Competence can be natural, as observed in certain bacteria and archaea, or artificially induced in the...
709
Position Vectors
1.8K
A position vector is a fundamental concept in mathematics that helps determine the position of one point with respect to another point in space. It is a vector that describes the direction and distance between two points. Position vectors are highly useful in the field of math and science, as they help represent spatial relationships and make calculations easier.
For instance, we want to locate a point P(x, y, z) relative to the origin of coordinates O. In that case, we can define a position...
For instance, we want to locate a point P(x, y, z) relative to the origin of coordinates O. In that case, we can define a position...
1.8K


