arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2207.01066cs.LGcs.CV
收藏

NP-Match:当神经过程满足半监督学习

NP-Match: When Neural Processes meet Semi-Supervised Learning

University of Oxford(牛津大学);TU Wien(维也纳工业大学);Microsoft Research(微软研究院);Tsinghua University(清华大学);Rutgers University(罗格斯大学);Microsoft(微软)

Jianfeng Wang, Thomas Lukasiewicz, Daniela Massiceti, Xiaolin Hu, Vladimir Pavlovic, Alexandros Neophytou

摘要:

半监督学习(Semi-supervised learning,SSL)是近年来被广泛研究的一种利用未标记数据减少对标记数据依赖的有效方法。在这项工作中,我们调整神经过程(NPs)的半监督图像分类任务,从而在一个新的方法命名为NP-Match。NP-Match适合这项任务有两个原因。首先,NP-Match在进行预测时隐式地比较数据点,因此,每个未标记的数据点的预测受到与其相似的标记数据点的影响,这提高了伪标签的质量。其次,NP-Match能够估计不确定性,可以用作选择具有可靠伪标签的未标记样本的工具。与基于不确定性的蒙特卡罗(MC)退出实现的SSL方法相比,NP-Match估计不确定性的计算开销要少得多,这可以节省训练和测试阶段的时间。我们在四个公共数据集上进行了广泛的实验,NP-Match的性能优于最先进的(SOTA)结果或在它们上取得了竞争性结果,这表明了NP-Match的有效性及其在SSL中的潜力。

英文摘要:

Semi-supervised learning (SSL) has been widely explored in recent years, and it is an effective way of leveraging unlabeled data to reduce the reliance on labeled data. In this work, we adjust neural processes (NPs) to the semi-supervised image classification task, resulting in a new method named NP-Match. NP-Match is suited to this task for two reasons. Firstly, NP-Match implicitly compares data points when making predictions, and as a result, the prediction of each unlabeled data point is affected by the labeled data points that are similar to it, which improves the quality of pseudo-labels. Secondly, NP-Match is able to estimate uncertainty that can be used as a tool for selecting unlabeled samples with reliable pseudo-labels. Compared with uncertainty-based SSL methods implemented with Monte Carlo (MC) dropout, NP-Match estimates uncertainty with much less computational overhead, which can save time at both the training and the testing phases. We conducted extensive experiments on four public datasets, and NP-Match outperforms state-of-the-art (SOTA) results or achieves competitive results on them, which shows the effectiveness of NP-Match and its potential for SSL.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑