FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312387594> ?p ?o ?g. }

• W4312387594 abstract "Deep Learning (DL) has shown great promise in the unsupervised task of clustering. That said, while in classical (i.e., non-deep) clustering the benefits of the nonparametric approach are well known, most deep-clustering methods are parametric: namely, they require a predefined and fixed number of clusters, denoted by K. When <tex xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>$K$</tex> is unknown, however, using model-selection criteria to choose its optimal value might become computationally expensive, especially in DL as the training process would have to be repeated numerous times. In this work, we bridge this gap by introducing an effective deep-clustering method that does not require knowing the value of <tex xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>$K$</tex> as it infers it during the learning. Using a split/merge framework, a dynamic architecture that adapts to the changing <tex xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>$K$</tex> , and a novel loss, our proposed method outperforms existing nonparametric methods (both classical and deep ones). While the very few existing deep nonparametric methods lack scalability, we demonstrate ours by being the first to report the performance of such a method on ImageNet. We also demonstrate the importance of inferring <tex xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>$K$</tex> by showing how methods that fix it deteriorate in performance when their assumed <tex xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>$K$</tex> value gets further from the ground-truth one, especially on imbalanced datasets. Our code is available at https://github.com/BGU-CS-VIL/DeepDPM." @default.
• W4312387594 created "2023-01-04" @default.
• W4312387594 creator A5001269680 @default.
• W4312387594 creator A5077844530 @default.
• W4312387594 creator A5082095784 @default.
• W4312387594 date "2022-06-01" @default.
• W4312387594 modified "2023-10-02" @default.
• W4312387594 title "DeepDPM: Deep Clustering With an Unknown Number of Clusters" @default.
• W4312387594 cites W1967687583 @default.
• W4312387594 cites W2007339694 @default.
• W4312387594 cites W2019278527 @default.
• W4312387594 cites W2025416353 @default.
• W4312387594 cites W2025498056 @default.
• W4312387594 cites W2033012377 @default.
• W4312387594 cites W2039914296 @default.
• W4312387594 cites W2049633694 @default.
• W4312387594 cites W2069429561 @default.
• W4312387594 cites W2100003124 @default.
• W4312387594 cites W2100659887 @default.
• W4312387594 cites W2100730563 @default.
• W4312387594 cites W2108598243 @default.
• W4312387594 cites W2127498532 @default.
• W4312387594 cites W2128012710 @default.
• W4312387594 cites W2134135198 @default.
• W4312387594 cites W2158266063 @default.
• W4312387594 cites W2162021827 @default.
• W4312387594 cites W2210479033 @default.
• W4312387594 cites W2585956660 @default.
• W4312387594 cites W2806035899 @default.
• W4312387594 cites W2955007221 @default.
• W4312387594 cites W2986063762 @default.
• W4312387594 cites W2987741655 @default.
• W4312387594 cites W2987802279 @default.
• W4312387594 cites W2987860915 @default.
• W4312387594 cites W3003837024 @default.
• W4312387594 cites W3034671389 @default.
• W4312387594 cites W3077502225 @default.
• W4312387594 cites W3085482458 @default.
• W4312387594 cites W3100043883 @default.
• W4312387594 cites W3176613769 @default.
• W4312387594 cites W566164770 @default.
• W4312387594 doi "https://doi.org/10.1109/cvpr52688.2022.00963" @default.
• W4312387594 hasPublicationYear "2022" @default.
• W4312387594 type Work @default.
• W4312387594 citedByCount "10" @default.
• W4312387594 countsByYear W43123875942022 @default.
• W4312387594 countsByYear W43123875942023 @default.
• W4312387594 crossrefType "proceedings-article" @default.
• W4312387594 hasAuthorship W4312387594A5001269680 @default.
• W4312387594 hasAuthorship W4312387594A5077844530 @default.
• W4312387594 hasAuthorship W4312387594A5082095784 @default.
• W4312387594 hasBestOaLocation W43123875942 @default.
• W4312387594 hasConcept C102366305 @default.
• W4312387594 hasConcept C105795698 @default.
• W4312387594 hasConcept C108583219 @default.
• W4312387594 hasConcept C117251300 @default.
• W4312387594 hasConcept C119857082 @default.
• W4312387594 hasConcept C154945302 @default.
• W4312387594 hasConcept C33923547 @default.
• W4312387594 hasConcept C41008148 @default.
• W4312387594 hasConcept C48044578 @default.
• W4312387594 hasConcept C73555534 @default.
• W4312387594 hasConcept C77088390 @default.
• W4312387594 hasConceptScore W4312387594C102366305 @default.
• W4312387594 hasConceptScore W4312387594C105795698 @default.
• W4312387594 hasConceptScore W4312387594C108583219 @default.
• W4312387594 hasConceptScore W4312387594C117251300 @default.
• W4312387594 hasConceptScore W4312387594C119857082 @default.
• W4312387594 hasConceptScore W4312387594C154945302 @default.
• W4312387594 hasConceptScore W4312387594C33923547 @default.
• W4312387594 hasConceptScore W4312387594C41008148 @default.
• W4312387594 hasConceptScore W4312387594C48044578 @default.
• W4312387594 hasConceptScore W4312387594C73555534 @default.
• W4312387594 hasConceptScore W4312387594C77088390 @default.
• W4312387594 hasFunder F4320322252 @default.
• W4312387594 hasLocation W43123875941 @default.
• W4312387594 hasLocation W43123875942 @default.
• W4312387594 hasOpenAccess W4312387594 @default.
• W4312387594 hasPrimaryLocation W43123875941 @default.
• W4312387594 hasRelatedWork W3014300295 @default.
• W4312387594 hasRelatedWork W3164822677 @default.
• W4312387594 hasRelatedWork W4223943233 @default.
• W4312387594 hasRelatedWork W4225161397 @default.
• W4312387594 hasRelatedWork W4250304930 @default.
• W4312387594 hasRelatedWork W4312200629 @default.
• W4312387594 hasRelatedWork W4360585206 @default.
• W4312387594 hasRelatedWork W4364306694 @default.
• W4312387594 hasRelatedWork W4380075502 @default.
• W4312387594 hasRelatedWork W4380086463 @default.
• W4312387594 isParatext "false" @default.
• W4312387594 isRetracted "false" @default.
• W4312387594 workType "article" @default.