arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1804.02201cs.CV
收藏

用于模型提取和半监督学习的包围流形分割

Ensemble Manifold Segmentation for Model Distillation and Semi-supervised Learning

ETH Zurich(苏黎世联邦理工学院)

Dengxin Dai, Wen Li, Till Kroeger, Luc Van Gool

摘要:

流形理论一直是许多学习方法的核心概念。然而,学习具有流形结构的现代CNN并没有引起应有的关注,主要是因为将流形结构强加到CNN的架构上是不方便的。在本文中,我们提出了ManifoldNet,这是一种鼓励学习流形感知表示的新方法。我们的方法将输入流形分割成一组片段。通过将相应的分割id作为伪标签分配给每个样本,我们将保持局部流形结构的问题转化为逐点分类任务。由于其无监督的性质,分割往往是嘈杂的。我们通过引入集成流形分割(EMS)来缓解这一问题。EMS通过将训练数据划分为包含局部接近度样本的分类训练集的集合来说明流形结构。CNN在多任务学习框架下在这些集合上进行训练,以符合流形。ManifoldNet可以只使用伪标签或与特定任务的标签一起训练。我们在两个不同的任务上评估ManifoldNet:网络模仿(蒸馏)和半监督学习。我们的实验表明,流形结构有效地利用无监督和半监督学习。

英文摘要:

Manifold theory has been the central concept of many learning methods. However, learning modern CNNs with manifold structures has not raised due attention, mainly because of the inconvenience of imposing manifold structures onto the architecture of the CNNs. In this paper we present ManifoldNet, a novel method to encourage learning of manifold-aware representations. Our approach segments the input manifold into a set of fragments. By assigning the corresponding segmentation id as a pseudo label to every sample, we convert the problem of preserving the local manifold structure into a point-wise classification task. Due to its unsupervised nature, the segmentation tends to be noisy. We mitigate this by introducing ensemble manifold segmentation (EMS). EMS accounts for the manifold structure by dividing the training data into an ensemble of classification training sets that contain samples of local proximity. CNNs are trained on these ensembles under a multi-task learning framework to conform to the manifold. ManifoldNet can be trained with only the pseudo labels or together with task-specific labels. We evaluate ManifoldNet on two different tasks: network imitation (distillation) and semi-supervised learning. Our experiments show that the manifold structures are effectively utilized for both unsupervised and semi-supervised learning.

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。

↑