HIRI-ViT:使用高分辨率输入扩展视觉变压器
概括
我们介绍HIRI-ViT,这是一种用于计算机视觉任务的新型混合深度学习骨干. 该模型有效处理高分辨率图像,实现图像识别和密集预测基准的最新精度.
科学领域:
- 计算机视觉 计算机视觉
- 深度学习架构 深度学习架构
- 图像识别 图像识别
背景情况:
- 结合视觉变换器 (ViT) 和卷积神经网络 (CNN) 的混合深度模型对于视觉任务是有效的.
- 增加输入分辨率增强了模型容量,但导致了昂贵的计算,二次缩放成本.
- 现有的混合骨干在处理高分辨率输入时难以提高效率.
研究的目的:
- 开发一种新的混合深层骨干,HIRI-ViT,专门设计用于高分辨率输入的高效处理.
- 通过解决高分辨率输入的二次缩放问题来提高视觉任务中的计算效率和模型性能.
- 通过具有成本效益的架构,在图像识别和密集的预测任务中建立一个新的最先进的状态.
主要方法:
- 拟议的HIRI-ViT,一个为高分辨率输入量身定制的五阶段视觉转换器 (ViT) 骨干.
- 实施了一种新的方法,将CNN的操作分解成两个平行分支:一个是高分辨率的,卷积较少,另一个是低分辨率的,在下方采样后卷积较多.
- 在ImageNet-1K (识别) 和COCO,ADE20K (密度预测) 数据集上评估了HIRI-ViT.
主要成果:
- 在图像识别和密集预测任务上,HIRI-ViT表现出卓越的性能.
- 在ImageNet上以448x448输入实现了84.3%的最佳发布的Top-1准确度,超过了以前的方法.
- 在可比计算成本 (~5.0 GFLOPs) 下,与iFormer-S.等现有模型相比,HIRI-ViT显著提高了准确性.
结论:
- 在深度学习中,HIRI-ViT为处理高分辨率图像提供了高效和计算效率的解决方案.
- 拟议的并行CNN分支分解有效平衡功能分辨率和计算成本.
- HIRI-ViT为视觉任务的性能设定了新的基准,特别是用于高分辨率图像分析.
相关概念视频
Transformers with Off-Nominal Turns Ratios
152
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...
152
Types Of Transformers
974
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...
974
Reducing Line Loss
152
In a three-phase circuit, line loss is an indicator of energy dissipated as heat due to the resistance of transmission lines. To address this, incorporating transformers into the system—a step-up transformer at the source and a step-down transformer at the load—is a strategic solution. Two three-phase transformers are introduced to improve this.
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
With a step-up transformer at the source, the voltage is increased, thereby reducing the current in the transmission lines since power loss...
152
Depth Perception and Spatial Vision
646
Depth perception is the ability to perceive objects three-dimensionally. It relies on two types of cues: binocular and monocular. Binocular cues depend on the combination of images from both eyes and how the eyes work together. Since the eyes are in slightly different positions, each eye captures a slightly different image. This disparity between images, known as binocular disparity, helps the brain interpret depth. When the brain compares these images, it determines the distance to an object.
646
The Ideal Transformer
391
In single-phase two-winding transformers, two windings are coiled around a magnetic core characterized by cross-sectional area A and magnetic permeability μ. A phasor current i1 enters the left winding while i2 exits the right winding, establishing the fundamental working of the transformer through electromagnetic principles.
Ampere's Law forms the basis of understanding the magnetic field within the transformer. It states that the integral of the magnetic field intensity's...
Ampere's Law forms the basis of understanding the magnetic field within the transformer. It states that the integral of the magnetic field intensity's...
391
Transformers in Distribution System
102
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...
102


