FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W646953574> ?p ?o ?g. }

• W646953574 abstract "In this paper, we investigate the problem of learning feature representation from unlabeled data using a single-layer K-means network. A K-means network maps the input data into a feature representation by finding the nearest centroid for each input point, which has attracted researchers' great attention recently due to its simplicity, effectiveness, and scalability. However, one drawback of this feature mapping is that it tends to be unreliable when the training data contains noise. To address this issue, we propose a SVDD based feature learning algorithm that describes the density and distribution of each cluster from K-means with an SVDD ball for more robust feature representation. For this purpose, we present a new SVDD algorithm called C-SVDD that centers the SVDD ball towards the mode of local density of each cluster, and we show that the objective of C-SVDD can be solved very efficiently as a linear programming problem. Additionally, traditional unsupervised feature learning methods usually take an average or sum of local representations to obtain global representation which ignore spatial relationship among them. To use spatial information we propose a global representation with a variant of SIFT descriptor. The architecture is also extended with multiple receptive field scales and multiple pooling sizes. Extensive experiments on several popular object recognition benchmarks, such as STL-10, MINST, Holiday and Copydays shows that the proposed C-SVDDNet method yields comparable or better performance than that of the previous state of the art methods." @default.
• W646953574 created "2016-06-24" @default.
• W646953574 creator A5004478562 @default.
• W646953574 creator A5046454314 @default.
• W646953574 date "2014-12-23" @default.
• W646953574 modified "2023-10-17" @default.
• W646953574 title "Unsupervised Feature Learning with C-SVDDNet" @default.
• W646953574 cites W1694178301 @default.
• W646953574 cites W1799366690 @default.
• W646953574 cites W187956566 @default.
• W646953574 cites W189596042 @default.
• W646953574 cites W1907282891 @default.
• W646953574 cites W1970088130 @default.
• W646953574 cites W1976921161 @default.
• W646953574 cites W1984309565 @default.
• W646953574 cites W2002648693 @default.
• W646953574 cites W2018431010 @default.
• W646953574 cites W2020308406 @default.
• W646953574 cites W2020719522 @default.
• W646953574 cites W2093627685 @default.
• W646953574 cites W2093810479 @default.
• W646953574 cites W2100495367 @default.
• W646953574 cites W2103924867 @default.
• W646953574 cites W2106665752 @default.
• W646953574 cites W2112796928 @default.
• W646953574 cites W2118858186 @default.
• W646953574 cites W2128744540 @default.
• W646953574 cites W2130325614 @default.
• W646953574 cites W2134557905 @default.
• W646953574 cites W2159540339 @default.
• W646953574 cites W2161893161 @default.
• W646953574 cites W2163922914 @default.
• W646953574 cites W2166118928 @default.
• W646953574 cites W2168894214 @default.
• W646953574 cites W2169488311 @default.
• W646953574 cites W2169624977 @default.
• W646953574 cites W2217045154 @default.
• W646953574 cites W2433935537 @default.
• W646953574 cites W2546302380 @default.
• W646953574 cites W2949578333 @default.
• W646953574 cites W2950789693 @default.
• W646953574 cites W2952390042 @default.
• W646953574 cites W4919037 @default.
• W646953574 doi "https://doi.org/10.48550/arxiv.1412.7259" @default.
• W646953574 hasPublicationYear "2014" @default.
• W646953574 type Work @default.
• W646953574 sameAs 646953574 @default.
• W646953574 citedByCount "2" @default.
• W646953574 countsByYear W6469535742015 @default.
• W646953574 countsByYear W6469535742016 @default.
• W646953574 crossrefType "posted-content" @default.
• W646953574 hasAuthorship W646953574A5004478562 @default.
• W646953574 hasAuthorship W646953574A5046454314 @default.
• W646953574 hasBestOaLocation W6469535741 @default.
• W646953574 hasConcept C119857082 @default.
• W646953574 hasConcept C124101348 @default.
• W646953574 hasConcept C138885662 @default.
• W646953574 hasConcept C146599234 @default.
• W646953574 hasConcept C153180895 @default.
• W646953574 hasConcept C154945302 @default.
• W646953574 hasConcept C2776401178 @default.
• W646953574 hasConcept C41008148 @default.
• W646953574 hasConcept C41895202 @default.
• W646953574 hasConcept C52622490 @default.
• W646953574 hasConcept C59404180 @default.
• W646953574 hasConcept C61265191 @default.
• W646953574 hasConceptScore W646953574C119857082 @default.
• W646953574 hasConceptScore W646953574C124101348 @default.
• W646953574 hasConceptScore W646953574C138885662 @default.
• W646953574 hasConceptScore W646953574C146599234 @default.
• W646953574 hasConceptScore W646953574C153180895 @default.
• W646953574 hasConceptScore W646953574C154945302 @default.
• W646953574 hasConceptScore W646953574C2776401178 @default.
• W646953574 hasConceptScore W646953574C41008148 @default.
• W646953574 hasConceptScore W646953574C41895202 @default.
• W646953574 hasConceptScore W646953574C52622490 @default.
• W646953574 hasConceptScore W646953574C59404180 @default.
• W646953574 hasConceptScore W646953574C61265191 @default.
• W646953574 hasLocation W6469535741 @default.
• W646953574 hasOpenAccess W646953574 @default.
• W646953574 hasPrimaryLocation W6469535741 @default.
• W646953574 hasRelatedWork W1582226822 @default.
• W646953574 hasRelatedWork W1983120175 @default.
• W646953574 hasRelatedWork W2022942246 @default.
• W646953574 hasRelatedWork W2344014954 @default.
• W646953574 hasRelatedWork W2621332360 @default.
• W646953574 hasRelatedWork W2738461075 @default.
• W646953574 hasRelatedWork W2801009187 @default.
• W646953574 hasRelatedWork W2950902107 @default.
• W646953574 hasRelatedWork W3080336085 @default.
• W646953574 hasRelatedWork W3110278283 @default.
• W646953574 isParatext "false" @default.
• W646953574 isRetracted "false" @default.
• W646953574 magId "646953574" @default.
• W646953574 workType "article" @default.