Outlier Cluster Formation in Spectral Clustering
This addresses outlier handling in clustering for applications like photo organization and surveillance, but it is incremental as it builds on existing spectral clustering methods.
The paper tackles outlier detection and cluster number estimation in spectral clustering by revealing its outlier cluster formation property and designing an evaluation function, achieving state-of-the-art performance in face clustering and person re-identification tasks.
Outlier detection and cluster number estimation is an important issue for clustering real data. This paper focuses on spectral clustering, a time-tested clustering method, and reveals its important properties related to outliers. The highlights of this paper are the following two mathematical observations: first, spectral clustering's intrinsic property of an outlier cluster formation, and second, the singularity of an outlier cluster with a valid cluster number. Based on these observations, we designed a function that evaluates clustering and outlier detection results. In experiments, we prepared two scenarios, face clustering in photo album and person re-identification in a camera network. We confirmed that the proposed method detects outliers and estimates the number of clusters properly in both problems. Our method outperforms state-of-the-art methods in both the 128-dimensional sparse space for face clustering and the 4,096-dimensional non-sparse space for person re-identification.