arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1801.04438cs.CV
收藏

半监督Fisher向量网络

Semi-supervised Fisher vector network

Queen Mary University of London(伦敦玛丽女王大学)

Petar Palasek, Ioannis Patras

摘要:

在这项工作中,我们探索了[8]中提出的架构,它表达了经典Fisher向量管道方法的处理步骤,即通过主成分分析(PCA)投影,高斯混合模型(GMM)和Fisher向量描述符提取作为网络层的降维,可以修改为混合网络,结合无监督和监督训练方法的优点,从而产生学习所述输入数据的半监督Fisher向量描述符的模型。我们评估了所提出的模型在图像分类和动作识别问题,并显示了模型的分类性能如何提高,在训练过程中的未标记数据量的增加。

英文摘要:

In this work we explore how the architecture proposed in [8], which expresses the processing steps of the classical Fisher vector pipeline approaches, i.e. dimensionality reduction by principal component analysis (PCA) projection, Gaussian mixture model (GMM) and Fisher vector descriptor extraction as network layers, can be modified into a hybrid network that combines the benefits of both unsupervised and supervised training methods, resulting in a model that learns a semi-supervised Fisher vector descriptor of the input data. We evaluate the proposed model at image classification and action recognition problems and show how the model's classification performance improves as the amount of unlabeled data increases during training.

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。

↑