Matches in SemOpenAlex for { <https://semopenalex.org/work/W2993035999> ?p ?o ?g. }
- W2993035999 endingPage "23" @default.
- W2993035999 startingPage "10" @default.
- W2993035999 abstract "Although supervised deep representation learning has attracted enormous attentions across areas of pattern recognition and computer vision, little progress has been made towards unsupervised deep representation learning for image clustering. In this paper, we propose a deep spectral analysis network for unsupervised representation learning and image clustering. While spectral analysis is established with solid theoretical foundations and has been widely applied to unsupervised data mining, its essential weakness lies in the fact that it is difficult to construct a proper affinity matrix and determine the involving Laplacian matrix for a given dataset. In this paper, we propose a SA-Net to overcome these weaknesses and achieve improved image clustering by extending the spectral analysis procedure into a deep learning framework with multiple layers. The SA-Net has the capability to learn deep representations and reveal deep correlations among data samples. Compared with the existing spectral analysis, the SA-Net achieves two advantages: (i) Given the fact that one spectral analysis procedure can only deal with one subset of the given dataset, our proposed SA-Net elegantly integrates multiple parallel and consecutive spectral analysis procedures together to enable interactive learning across different units towards a coordinated clustering model; (ii) Our SA-Net can identify the local similarities among different images at patch level and hence achieves a higher level of robustness against occlusions. Extensive experiments on a number of popular datasets support that our proposed SA-Net outperforms 11 benchmarks across a number of image clustering applications." @default.
- W2993035999 created "2019-12-13" @default.
- W2993035999 creator A5005727907 @default.
- W2993035999 creator A5045867920 @default.
- W2993035999 date "2020-03-01" @default.
- W2993035999 modified "2023-10-14" @default.
- W2993035999 title "SA-Net: A deep spectral analysis network for image clustering" @default.
- W2993035999 cites W1968886315 @default.
- W2993035999 cites W2041362950 @default.
- W2993035999 cites W2100495367 @default.
- W2993035999 cites W2112796928 @default.
- W2993035999 cites W2116810533 @default.
- W2993035999 cites W2121947440 @default.
- W2993035999 cites W2123921160 @default.
- W2993035999 cites W2131828344 @default.
- W2993035999 cites W2132914434 @default.
- W2993035999 cites W2135957668 @default.
- W2993035999 cites W2153233077 @default.
- W2993035999 cites W2164136210 @default.
- W2993035999 cites W2322020277 @default.
- W2993035999 cites W2568618480 @default.
- W2993035999 cites W2603986758 @default.
- W2993035999 cites W2768370210 @default.
- W2993035999 cites W2790655810 @default.
- W2993035999 cites W2804557543 @default.
- W2993035999 cites W2883493457 @default.
- W2993035999 cites W2889369603 @default.
- W2993035999 cites W2964213043 @default.
- W2993035999 cites W3102431071 @default.
- W2993035999 doi "https://doi.org/10.1016/j.neucom.2019.11.078" @default.
- W2993035999 hasPublicationYear "2020" @default.
- W2993035999 type Work @default.
- W2993035999 sameAs 2993035999 @default.
- W2993035999 citedByCount "13" @default.
- W2993035999 countsByYear W29930359992020 @default.
- W2993035999 countsByYear W29930359992021 @default.
- W2993035999 countsByYear W29930359992022 @default.
- W2993035999 countsByYear W29930359992023 @default.
- W2993035999 crossrefType "journal-article" @default.
- W2993035999 hasAuthorship W2993035999A5005727907 @default.
- W2993035999 hasAuthorship W2993035999A5045867920 @default.
- W2993035999 hasBestOaLocation W29930359992 @default.
- W2993035999 hasConcept C104317684 @default.
- W2993035999 hasConcept C105611402 @default.
- W2993035999 hasConcept C108583219 @default.
- W2993035999 hasConcept C115178988 @default.
- W2993035999 hasConcept C119857082 @default.
- W2993035999 hasConcept C124101348 @default.
- W2993035999 hasConcept C132525143 @default.
- W2993035999 hasConcept C14166107 @default.
- W2993035999 hasConcept C153180895 @default.
- W2993035999 hasConcept C154945302 @default.
- W2993035999 hasConcept C17744445 @default.
- W2993035999 hasConcept C185592680 @default.
- W2993035999 hasConcept C199539241 @default.
- W2993035999 hasConcept C2524010 @default.
- W2993035999 hasConcept C2776359362 @default.
- W2993035999 hasConcept C33923547 @default.
- W2993035999 hasConcept C41008148 @default.
- W2993035999 hasConcept C55493867 @default.
- W2993035999 hasConcept C63479239 @default.
- W2993035999 hasConcept C73555534 @default.
- W2993035999 hasConcept C8038995 @default.
- W2993035999 hasConcept C80444323 @default.
- W2993035999 hasConcept C94625758 @default.
- W2993035999 hasConceptScore W2993035999C104317684 @default.
- W2993035999 hasConceptScore W2993035999C105611402 @default.
- W2993035999 hasConceptScore W2993035999C108583219 @default.
- W2993035999 hasConceptScore W2993035999C115178988 @default.
- W2993035999 hasConceptScore W2993035999C119857082 @default.
- W2993035999 hasConceptScore W2993035999C124101348 @default.
- W2993035999 hasConceptScore W2993035999C132525143 @default.
- W2993035999 hasConceptScore W2993035999C14166107 @default.
- W2993035999 hasConceptScore W2993035999C153180895 @default.
- W2993035999 hasConceptScore W2993035999C154945302 @default.
- W2993035999 hasConceptScore W2993035999C17744445 @default.
- W2993035999 hasConceptScore W2993035999C185592680 @default.
- W2993035999 hasConceptScore W2993035999C199539241 @default.
- W2993035999 hasConceptScore W2993035999C2524010 @default.
- W2993035999 hasConceptScore W2993035999C2776359362 @default.
- W2993035999 hasConceptScore W2993035999C33923547 @default.
- W2993035999 hasConceptScore W2993035999C41008148 @default.
- W2993035999 hasConceptScore W2993035999C55493867 @default.
- W2993035999 hasConceptScore W2993035999C63479239 @default.
- W2993035999 hasConceptScore W2993035999C73555534 @default.
- W2993035999 hasConceptScore W2993035999C8038995 @default.
- W2993035999 hasConceptScore W2993035999C80444323 @default.
- W2993035999 hasConceptScore W2993035999C94625758 @default.
- W2993035999 hasFunder F4320321001 @default.
- W2993035999 hasLocation W29930359991 @default.
- W2993035999 hasLocation W29930359992 @default.
- W2993035999 hasOpenAccess W2993035999 @default.
- W2993035999 hasPrimaryLocation W29930359991 @default.
- W2993035999 hasRelatedWork W2597787948 @default.
- W2993035999 hasRelatedWork W3123344745 @default.
- W2993035999 hasRelatedWork W3192794374 @default.
- W2993035999 hasRelatedWork W3208584567 @default.
- W2993035999 hasRelatedWork W4221031031 @default.