多尺度密度预测变压器的知识蒸,用于自我监督的深度估计.
1Division of Electronic Engineering, Jeonbuk National University, 567 Baekje-daero Deokjin-gu, Jeonju, 54896, Korea.
Scientific reports
|November 3, 2023
概括
这项研究引入了一种新的知识蒸方法,以改善自我监督的深度估计. 通过使用直接的深度线索,监督和自我监督方法之间的性能差距显著减少.
科学领域:
- 计算机视觉 计算机视觉
- 机器学习 机器学习
- 深度学习 (Deep Learning) 是一种深度学习.
背景情况:
- 从单个图像进行深度估计对于各种应用至关重要.
- 监督的方法需要外部传感器进行地面真相检测,这限制了它们的实用性.
- 自主监督方法避免地面真相数据,但与监督方法相比,性能落后.
研究的目的:
- 为了弥合监督和自我监督深度估计之间的绩效差距.
- 为自主监督深度网络开发更有效的培训策略.
- 为了利用直接的深度线索来提高准确性.
主要方法:
- 运用知识蒸 (教师-学生框架) 来转移知识.
- 使用自主监督的光度误差训练了一个教师网络.
- 开发了一种具有蒙特卡洛脱机的多尺度密集预测变压器.
- 建议使用一组随机估计的多尺度蒸损失.
主要成果:
- 在自我监督的深度估计中实现了最先进的精度.
- 证明了直接深度线索对光度误差的有效性.
- 在KITTI和Make3D数据集上验证了性能.
结论:
- 使用直接深度线索的知识蒸增强了自我监督的深度估计.
- 拟议的多级蒸损失可以改善网络培训.
- 这种方法为实际的单图像深度估计提供了一个有希望的方向.
相关概念视频
01:19Survival Tree
88
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
Building a Survival Tree
Constructing a...
Building a Survival Tree
Constructing a...
88
01:15Depth Perception and Spatial Vision
678
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.
678