arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.04009cs.CV
收藏

斜流形上的Transductive Few-Shot分类

Transductive Few-Shot Classification on the Oblique Manifold

College of Information Science and Electronic Engineering, Zhejiang University(浙江大学信息科学与电子工程学院);ZJU-League Research & Development Center(ZJU-League研发中心);State Key Lab of CAD&CG, Zhejiang University(浙江大学CAD&CG国家重点实验室)

Guodong Qi, Huimin Yu, Zhaohui Lu, Shuzhao Li

摘要:

少样本学习(FSL)试图利用有限的数据进行学习。在这项工作中,我们执行的特征提取在欧几里德空间和测地线距离度量上的斜流形(OM)。特别地,为了更好地提取特征提取,我们提出了一种非参数区域自注意空间金字塔池(RSSPP),实现了泛化能力和区分能力之间的权衡的单一图像特征。然后,我们将特征作为点嵌入OM。此外,我们设计了一个基于倾斜距离的分类器(ODC),实现分类的切线空间,更好地近似OM本地可学习的切点。最后,我们提出了一种新的参数初始化方法和一种新的损失函数。大量的实验证明了我们的算法的有效性,它优于最先进的方法在流行的基准测试:mini-ImageNet,tiered-ImageNet和Caltech-UCSD Birds-200-2011(CUB)。

英文摘要:

Few-shot learning (FSL) attempts to learn with limited data. In this work, we perform the feature extraction in the Euclidean space and the geodesic distance metric on the Oblique Manifold (OM). Specially, for better feature extraction, we propose a non-parametric Region Self-attention with Spatial Pyramid Pooling (RSSPP), which realizes a trade-off between the generalization and the discriminative ability of the single image feature. Then, we embed the feature to OM as a point. Furthermore, we design an Oblique Distance-based Classifier (ODC) that achieves classification in the tangent spaces which better approximate OM locally by learnable tangency points. Finally, we introduce a new method for parameters initialization and a novel loss function in the transductive settings. Extensive experiments demonstrate the effectiveness of our algorithm and it outperforms state-of-the-art methods on the popular benchmarks: mini-ImageNet, tiered-ImageNet, and Caltech-UCSD Birds-200-2011 (CUB).

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。

↑