混合扩散：用于流形排序的谱-时间图滤波
Hybrid Diffusion: Spectral-Temporal Graph Filtering for Manifold Ranking
摘要：
最先进的图像检索性能的实现与CNN功能和流形排名使用的k-NN相似性图，预先计算离线。现有的两种最成功的方法是时间滤波，其中流形排名相当于在线求解稀疏线性系统，和谱滤波，其中离线执行邻接矩阵的特征分解，然后流形排名相当于在线点积搜索。前者遭受昂贵的查询和后者从显着的空间开销。在这里，我们介绍了一种新的，理论上有根据的混合滤波方法，允许完全控制这两个极端之间的时空权衡。实验上，我们验证了我们的混合方法提供的结果与最先进的水平，与光谱滤波方法相比，内存需求更低，与时间滤波相比，速度更快。
英文摘要：
State of the art image retrieval performance is achieved with CNN features and manifold ranking using a k-NN similarity graph that is pre-computed off-line. The two most successful existing approaches are temporal filtering, where manifold ranking amounts to solving a sparse linear system online, and spectral filtering, where eigen-decomposition of the adjacency matrix is performed off-line and then manifold ranking amounts to dot-product search online. The former suffers from expensive queries and the latter from significant space overhead. Here we introduce a novel, theoretically well-founded hybrid filtering approach allowing full control of the space-time trade-off between these two extremes. Experimentally, we verify that our hybrid method delivers results on par with the state of the art, with lower memory demands compared to spectral filtering approaches and faster compared to temporal filtering.
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。
