Matches in SemOpenAlex for { <https://semopenalex.org/work/W3205220782> ?p ?o ?g. }
- W3205220782 abstract "State-of-the-art subspace clustering methods are based on self-expressive model, which represents each data point as a linear combination of other data points. However, such methods are designed for a finite sample dataset and lack the ability to generalize to out-of-sample data. Moreover, since the number of self-expressive coefficients grows quadratically with the number of data points, their ability to handle large-scale datasets is often limited. In this paper, we propose a novel framework for subspace clustering, termed Self-Expressive Network (SENet), which employs a properly designed neural network to learn a self-expressive representation of the data. We show that our SENet can not only learn the self-expressive coefficients with desired properties on the training data, but also handle out-of-sample data. Besides, we show that SENet can also be leveraged to perform subspace clustering on large-scale datasets. Extensive experiments conducted on synthetic data and real world benchmark data validate the effectiveness of the proposed method. In particular, SENet yields highly competitive performance on MNIST, Fashion MNIST and Extended MNIST and state-of-the-art performance on CIFAR-10. The code is available at https://github.com/zhangsz1998/Self-Expressive-Network." @default.
- W3205220782 created "2021-10-25" @default.
- W3205220782 creator A5011256828 @default.
- W3205220782 creator A5027039492 @default.
- W3205220782 creator A5064317084 @default.
- W3205220782 creator A5088196538 @default.
- W3205220782 date "2021-10-08" @default.
- W3205220782 modified "2023-10-09" @default.
- W3205220782 title "Learning a Self-Expressive Network for Subspace Clustering" @default.
- W3205220782 cites W1592592706 @default.
- W3205220782 cites W1600471557 @default.
- W3205220782 cites W1826223126 @default.
- W3205220782 cites W1908089688 @default.
- W3205220782 cites W1966872876 @default.
- W3205220782 cites W1993962865 @default.
- W3205220782 cites W2003217181 @default.
- W3205220782 cites W2013712253 @default.
- W3205220782 cites W2025391886 @default.
- W3205220782 cites W2037549374 @default.
- W3205220782 cites W2040329636 @default.
- W3205220782 cites W2068510557 @default.
- W3205220782 cites W2072072671 @default.
- W3205220782 cites W2103943817 @default.
- W3205220782 cites W2112796928 @default.
- W3205220782 cites W2118103795 @default.
- W3205220782 cites W2118154608 @default.
- W3205220782 cites W2118348786 @default.
- W3205220782 cites W2121947440 @default.
- W3205220782 cites W2125742596 @default.
- W3205220782 cites W2127218421 @default.
- W3205220782 cites W2129812935 @default.
- W3205220782 cites W2132914434 @default.
- W3205220782 cites W2139054653 @default.
- W3205220782 cites W2144902590 @default.
- W3205220782 cites W2145152441 @default.
- W3205220782 cites W2151417892 @default.
- W3205220782 cites W2160616617 @default.
- W3205220782 cites W2294644361 @default.
- W3205220782 cites W2313932751 @default.
- W3205220782 cites W2343516804 @default.
- W3205220782 cites W2404771443 @default.
- W3205220782 cites W2526075485 @default.
- W3205220782 cites W2527399347 @default.
- W3205220782 cites W2532206188 @default.
- W3205220782 cites W2549661379 @default.
- W3205220782 cites W2571899125 @default.
- W3205220782 cites W2605920867 @default.
- W3205220782 cites W2608862709 @default.
- W3205220782 cites W2611378001 @default.
- W3205220782 cites W2615383372 @default.
- W3205220782 cites W2736399023 @default.
- W3205220782 cites W2736773830 @default.
- W3205220782 cites W2752230697 @default.
- W3205220782 cites W2779692282 @default.
- W3205220782 cites W2789015378 @default.
- W3205220782 cites W2798559986 @default.
- W3205220782 cites W2886216085 @default.
- W3205220782 cites W2940612076 @default.
- W3205220782 cites W2948062364 @default.
- W3205220782 cites W2953791858 @default.
- W3205220782 cites W2962852342 @default.
- W3205220782 cites W2962911132 @default.
- W3205220782 cites W2962937761 @default.
- W3205220782 cites W2963091558 @default.
- W3205220782 cites W2963165461 @default.
- W3205220782 cites W2963263347 @default.
- W3205220782 cites W2963365397 @default.
- W3205220782 cites W2963403868 @default.
- W3205220782 cites W2963761396 @default.
- W3205220782 cites W2963840432 @default.
- W3205220782 cites W2963858333 @default.
- W3205220782 cites W2964074409 @default.
- W3205220782 cites W2964121744 @default.
- W3205220782 cites W2964275228 @default.
- W3205220782 cites W2970297355 @default.
- W3205220782 cites W2979359553 @default.
- W3205220782 cites W2979685515 @default.
- W3205220782 cites W2994560339 @default.
- W3205220782 cites W2994884162 @default.
- W3205220782 cites W2997927623 @default.
- W3205220782 cites W3011696451 @default.
- W3205220782 cites W3034425668 @default.
- W3205220782 cites W3088544011 @default.
- W3205220782 cites W3099880660 @default.
- W3205220782 cites W3103253955 @default.
- W3205220782 cites W3112808477 @default.
- W3205220782 cites W3118608800 @default.
- W3205220782 cites W3129311707 @default.
- W3205220782 cites W3137767720 @default.
- W3205220782 cites W56210758 @default.
- W3205220782 cites W79405465 @default.
- W3205220782 cites W2759684359 @default.
- W3205220782 doi "https://doi.org/10.48550/arxiv.2110.04318" @default.
- W3205220782 hasPublicationYear "2021" @default.
- W3205220782 type Work @default.
- W3205220782 sameAs 3205220782 @default.
- W3205220782 citedByCount "0" @default.
- W3205220782 crossrefType "posted-content" @default.
- W3205220782 hasAuthorship W3205220782A5011256828 @default.
- W3205220782 hasAuthorship W3205220782A5027039492 @default.