Zhang, TongJi, PanHarandi, MehrtashHartley, RichardReid, IanJawahar, CLi, HMori, GSchindler, K2023-07-18December 2978-3-030-20886-8http://hdl.handle.net/1885/294331Subspace clustering algorithms are notorious for their scalability issues because building and processing large affinity matrices are demanding. In this paper, we introduce a method that simultaneously learns an embedding space along subspaces within it to minimize a notion of reconstruction error, thus addressing the problem of subspace clustering in an end-to-end learning paradigm. To achieve our goal, we propose a scheme to update subspaces within a deep neural network. This in turn frees us from the need of having an affinity matrix to perform clustering. Unlike previous attempts, our method can easily scale up to large datasets, making it unique in the context of unsupervised learning with deep architectures. Our experiments show that our method significantly improves the clustering accuracy while enjoying cheaper memory footprints.This research was supported by Australian Research Council (ARC) Discovery Projects funding scheme (project DP150104645), ARC through Laureate Fellowship FL130100102 to IDR and ARC of Excellence for Robotic Vision (project number CE140100016).application/pdfen-AU© Springer Nature Switzerland AG 2019Subspace clusteringDeep learningScalable201910.1007/978-3-030-20873-8_302022-05-08