相关实验视频

Updated: Jun 11, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

轻量级单眼深度估计使用融合改进的变压器

Xin Sui¹, Song Gao², Aigong Xu¹

¹School of Geomatics, Liaoning Technical University, Fuxin, 123000, China.

Scientific reports

|September 28, 2024

概括

这项研究引入了一个轻量级的深度学习网络,用于准确的深度估计. 这种新的架构结合了卷积神经网络 (CNN) 和变压器,以实现高效的本地和全球特征提取,实现高精度和实时性能.

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.
人工智能的人工智能

背景情况:

现有的深度估计网络往往将准确性优先于计算效率.
需要轻量级模型,可以捕捉本地和全球图像特征,以有效估计深度.

研究的目的:

提出一个轻量级,自我监督的网络,用于准确和高效的深度估计.
整合卷积神经网络 (CNN) 和变压器,以增强特征提取.

主要方法:

一个浅的CNN,具有深度可分离的卷积,用于改进受体场.
具有多深度可分离卷积头的变压器转换了注意模块,以减少计算负载.
为了更好的非线性表示,Feedforward网络中采用了双步门机制.

主要成果:

拟议的网络与其他轻量级模型相比,在较少的参数中实现了更高的估计准确性.
在各种户外数据集中表现出卓越的概括性.
实现87 FPS的快速推断速度,平衡速度和准确性.

结论:

集成的CNN-Transformer网络有效地捕捉了当地和全球的背景,以进行深度估计.
该模型为需要高效准确的深度估计的实时应用提供了引人注目的解决方案.

关键词:

在美国,CNN是CNN.轻量化轻量化轻量化轻量化轻量化单眼深度估计的估计方法自我监督自我监督变压器变压器变压器

更多相关视频

Author Spotlight: Integrating Ultrasound Imaging with Biochemical Markers for Thyroid Disease Diagnosis

Author Spotlight: Integrating Ultrasound Imaging with Biochemical Markers for Thyroid Disease Diagnosis

Published on: February 9, 2024

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

相关概念视频

Depth Perception and Spatial Vision

Depth Perception and Spatial Vision

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.