OTAMatch:使用PseudoNCE进行最佳运输分配,用于半监督学习
概括
OTAMatch通过将伪标签重新定义为最佳传输问题来增强半监督学习,减少确认偏差并改善数据利用. 这种新的框架在具有挑战性的基准标准上取得了最先进的结果.
科学领域:
- 机器学习 机器学习
- 计算机科学 计算机科学
背景情况:
- 半监督学习 (SSL) 经常使用自主训练与一致性规范化.
- 现有的方法使用值启发式来管理标签噪声,但这可能会丢弃有价值的数据.
- 确认偏见和不充分利用歧视性信息是关键的挑战.
研究的目的:
- 推出OTAMatch,一个新的SSL框架,解决基于值的伪标签的局限性.
- 通过有效利用高可信度数据来减轻确认偏差.
- 为了提高SSL算法的稳定性和性能,在杂的环境中.
主要方法:
- 重构伪标签作为一个最佳运输 (OT) 赋值问题,通过凸最小化和Sinkhorn-Knopp算法解决.
- 整合了epsilon-greedy后部规范化和课程偏差校正,以实现强大的OT任务.
- 引入了PseudoNCE,以最大限度地提高相互信息的交换,并平衡融合速度与性能.
主要成果:
- 在各种SSL基准中,OTAMatch表现出了竞争力的表现.
- 与ImageNet上的SoftMatch相比,实现了显著的9.45%的错误率降低 (100K标签分割).
- 在具有挑战性的场景中,与最先进的SSL算法相比,其表现明显优于其他算法.
结论:
- OTAMatch提供了一种强大而有效的半监督学习方法,特别是在杂的环境中.
- 最佳的运输配方和综合策略提高了数据利用率和模型性能.
- 该框架代表了解决确认偏差和提高SSL有效性的重大进展.
相关概念视频
01:29Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
48
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
48
02:01Group Design
8.9K
The most basic experimental design involves two groups: the experimental group and the control group. The two groups are designed to be the same except for one difference— experimental manipulation. The experimental group gets the experimental manipulation—that is, the treatment or variable being tested—and the control group does not. Since experimental manipulation is the only difference between the experimental and control groups, we can be sure that any differences between...
8.9K
01:23Mechanistic Models: Compartment Models in Individual and Population Analysis
36
Mechanistic models are utilized in individual analysis using single-source data, but imperfections arise due to data collection errors, preventing perfect prediction of observed data. The mathematical equation involves known values (Xi), observed concentrations (Ci), measurement errors (εi), model parameters (ϕj), and the related function (ƒi) for i number of values. Different least-squares metrics quantify differences between predicted and observed values. The ordinary least...
36