Xun Xu, Loong-Fah Cheong, Zhuwen Li, Le Zhang and Ce Zhu
IEEE Transactions on Circuits and Systems for Video Technology, doi: 10.1109/TCSVT.2021.3069094
Publication year: 2021

Subspace clustering has been extensively studied from the hypothesis-and-test, algebraic, and spectral clustering-based perspectives. Most assume that only a single type/class of subspace is present. Generalizations to multiple types are non-trivial, plagued by challenges such as choice of types and numbers of models, sampling imbalance and parameter tuning. In many real world problems, data may not lie perfectly on a linear subspace and hand designed linear subspace models may not fit into these situations. In this work, we formulate the multi-type subspace clustering problem as one of learning non-linear subspace filters via deep multi-layer perceptrons (mlps). The response to the learnt subspace filters serve as the feature embedding that is clustering-friendly, i.e., points of the same clusters will be embedded closer together through the network. For inference, we apply K-means to the network output to cluster the data. Experiments are carried out on synthetic data and real world motion segmentation problems, producing state-of-the-art results. Project page is available at https://github.com/alex-xun-xu/LearnSubspaceMoSeg

发表评论

邮箱地址不会被公开。 必填项已用*标注