通过不确定性和阶级平衡重权重来增强持续的语义细分
概括
本研究引入了不确定性和类平衡重权重 (UCB) 方法,通过解决伪标签错误和类不平衡来改善持续的语义细分,显著减少模型遗忘.
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:
- 持续语义细分 (CSS) 旨在学习新的类别,而不忘记旧的类别.
- 由旧模型生成的伪标签至关重要,但如果错误,可能会导致遗忘.
- 在CSS中,阶级不平衡加剧了遗忘和混乱,超越了新与旧的类别.
研究的目的:
- 为了解决错误的伪标签对CSS模型遗忘的影响.
- 为了减轻在持续学习中因阶级不平衡造成的混乱.
- 通过解决这些被忽视的问题,提出一种新的方法来提高CSS性能.
主要方法:
- 引入了不确定性和类平衡重权衡 (UCB) 方法.
- UCB将较高的权重分配给具有较低伪标签不确定性的像素.
- 为了解决阶级不平衡,UCB还优先考虑比例较小的类别.
主要成果:
- 该UCB方法有效地减少模型忘记在持续的语义细分.
- 它根据数据集特征动态平衡类别权重.
- 实验表明,在Pascal-VOC和ADE20K数据集上的三个最先进的方法中,性能得到了改善.
结论:
- 拟议的UCB方法简单,有效,并且广泛适用于基于伪标签的CSS技术.
- 它增强了从关键像素的学习,从而更好地保留旧的类别.
- UCB提供了一个强大的解决方案,用于改进面临伪标签错误和类不平衡的持续语义细分模型.
相关概念视频
00:59Uncertainty: Overview
528
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.
528
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
01:29Aggregates Classification
305
Aggregate classification is generally based on its size, petrographic characteristics, weight, and source. Size classification ranges from coarse to fine aggregates, defined by the size of the particles. Coarse aggregates are particles that do not pass through ASTM sieve No. 4, and aggregates that pass through the sieve are fine aggregates.
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
305
00:59Propagation of Uncertainty from Random Error
655
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...
655
01:10Propagation of Uncertainty from Systematic Error
489
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...
489
01:31Classification of Systems-II
136
Continuous-time systems have continuous input and output signals, with time measured continuously. These systems are generally defined by differential or algebraic equations. For instance, in an RC circuit, the relationship between input and output voltage is expressed through a differential equation derived from Ohm's law and the capacitor relation,
136