对单眼深度估计的梯度基不确定性进行复习
概括
本研究介绍了一种基于梯度的方法,用于单眼深度估计中的不确定性估计. 该方法有效地识别了深度估计模型中不可靠的预测,而不需要重新培训.
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:
- 单眼深度估计对于自主系统至关重要,但容易因影子和动态物体等图像模糊性导致错误.
- 对于安全关键的应用程序来说,对像素智能不确定性评估至关重要,以标记不可靠的深度预测.
研究的目的:
- 为预先训练的单眼深度估计模型开发一种基于梯度的后期不确定性估计方法.
- 为了使可靠的不确定性评估在估计过程中不需要地面真相深度.
主要方法:
- 引入了一个辅助损失函数,利用预测的深度与通过数据增强生成的参考深度 (伪地面真相) 的一致性.
- 利用反向传播计算与特征图相关的衍生值,用于不确定性评分.
- 将该方法应用于现有的深度估计模型,而无需重新培训.
主要成果:
- 证明了基于梯度的不确定性估计对KITTI和NYU基准的有效性.
- 与相关方法相比,展示了优越的性能,特别是对于在易于不确定性的单眼序列上训练的模型.
- 验证了方法在不经再训练的情况下确定不确定性的能力.
结论:
- 提出的基于梯度的不确定性估计是单眼深度估计的简单,有效和计算效率高的后期解决方案.
- 该方法通过准确识别不确定区域,提高了安全关键应用的深度估计的可靠性.
- 这种方法比现有方法有了显著的改进,特别是在挑战单眼序列场景时.
相关概念视频
01:15Depth Perception and Spatial Vision
508
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.
508
00:59Uncertainty: Overview
496
In analytical chemistry, we often perform repetitive measurements to detect and minimize inaccuracies caused by both determinate and indeterminate errors. Despite the cares we take, the presence of random errors means that repeated measurements almost never have exactly the same magnitude. The collective difference between these measurements - observed values - and the estimated or expected value is called uncertainty. Uncertainty is conventionally written after the estimated or expected value.
496
00:59Propagation of Uncertainty from Random Error
621
An experiment often consists of more than a single step. In this case, measurements at each step give rise to uncertainty. Because the measurements occur in successive steps, the uncertainty in one step necessarily contributes to that in the subsequent step. As we perform statistical analysis on these types of experiments, we must learn to account for the propagation of uncertainty from one step to the next. The propagation of uncertainty depends on the type of arithmetic operation performed on...
621
00:54Uncertainty: Confidence Intervals
3.1K
The confidence interval is the range of values around the mean that contains the true mean. It is expressed as a probability percentage. The interpretation of a 95% confidence interval, for instance, is that the statistician is 95% confident that the true mean falls within the interval. The upper and lower limits of this range are known as confidence limits. The confidence limits for the true mean are estimated from the sample's mean, the standard deviation, and the statistical factor...
3.1K
01:10Propagation of Uncertainty from Systematic Error
453
The atomic mass of an element varies due to the relative ratio of its isotopes. A sample's relative proportion of oxygen isotopes influences its average atomic mass. For instance, if we were to measure the atomic mass of oxygen from a sample, the mass would be a weighted average of the isotopic masses of oxygen in that sample. Since a single sample is not likely to perfectly reflect the true atomic mass of oxygen for all the molecules of oxygen on Earth, the mass we obtain from this...
453
03:37Uncertainty in Measurement: Accuracy and Precision
73.1K
Scientists typically make repeated measurements of a quantity to ensure the quality of their findings and to evaluate both the precision and the accuracy of their results. Measurements are said to be precise if they yield very similar results when repeated in the same manner. A measurement is considered accurate if it yields a result that is very close to the true or the accepted value. Precise values agree with each other; accurate values agree with a true value.
73.1K