Matches in SemOpenAlex for { <https://semopenalex.org/work/W143357295> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W143357295 endingPage "643" @default.
- W143357295 startingPage "629" @default.
- W143357295 abstract "The usual frameworks for visual classification involve three steps: extracting features, building codebook and encoding features, and training classifiers. The current release of ImageNet dataset [1] with more than 14M images and 21K classes makes the problem of visual classification become more difficult to deal with. One of the most difficult tasks is to train a fast and accurate classifier. In this paper, we address this challenge by extending the state-of-the-art large scale classifier Power Mean SVM (PmSVM) proposed by Jianxin Wu [2] in two ways: (1) The first one is to build the balanced bagging classifiers with under-sampling strategy. Our algorithm avoids training on full data and the training process of PmSVM rapidly converges to the optimal solution, (2) The second one is to parallelize the training process of all classifiers with multi-core computers. We have developed the parallel versions of PmSVM based on high performance computing models. The evaluation on 1000 classes of ImageNet (ILSVRC 1000 [3]) shows that our approach is 90 times faster than the original implementation of PmSVM and 240 times faster than the state-of-the-art linear classifier (LIBLINEAR [4])." @default.
- W143357295 created "2016-06-24" @default.
- W143357295 creator A5020518940 @default.
- W143357295 creator A5026073604 @default.
- W143357295 creator A5069777977 @default.
- W143357295 date "2013-01-01" @default.
- W143357295 modified "2023-09-25" @default.
- W143357295 title "Large Scale Visual Classification with Many Classes" @default.
- W143357295 cites W1522956798 @default.
- W143357295 cites W1551774182 @default.
- W143357295 cites W1563938718 @default.
- W143357295 cites W1833138473 @default.
- W143357295 cites W1959000896 @default.
- W143357295 cites W2028870622 @default.
- W143357295 cites W2031489346 @default.
- W143357295 cites W2038597090 @default.
- W143357295 cites W2040672759 @default.
- W143357295 cites W2053229256 @default.
- W143357295 cites W2104167780 @default.
- W143357295 cites W2108598243 @default.
- W143357295 cites W2109235804 @default.
- W143357295 cites W2114846220 @default.
- W143357295 cites W2114968414 @default.
- W143357295 cites W2116339064 @default.
- W143357295 cites W2124509324 @default.
- W143357295 cites W2128154306 @default.
- W143357295 cites W2150953991 @default.
- W143357295 cites W2156909104 @default.
- W143357295 cites W2165966284 @default.
- W143357295 cites W2166049352 @default.
- W143357295 cites W2169308876 @default.
- W143357295 cites W2538008885 @default.
- W143357295 doi "https://doi.org/10.1007/978-3-642-39712-7_48" @default.
- W143357295 hasPublicationYear "2013" @default.
- W143357295 type Work @default.
- W143357295 sameAs 143357295 @default.
- W143357295 citedByCount "1" @default.
- W143357295 countsByYear W1433572952022 @default.
- W143357295 crossrefType "book-chapter" @default.
- W143357295 hasAuthorship W143357295A5020518940 @default.
- W143357295 hasAuthorship W143357295A5026073604 @default.
- W143357295 hasAuthorship W143357295A5069777977 @default.
- W143357295 hasConcept C154945302 @default.
- W143357295 hasConcept C205649164 @default.
- W143357295 hasConcept C2778755073 @default.
- W143357295 hasConcept C41008148 @default.
- W143357295 hasConcept C58640448 @default.
- W143357295 hasConceptScore W143357295C154945302 @default.
- W143357295 hasConceptScore W143357295C205649164 @default.
- W143357295 hasConceptScore W143357295C2778755073 @default.
- W143357295 hasConceptScore W143357295C41008148 @default.
- W143357295 hasConceptScore W143357295C58640448 @default.
- W143357295 hasLocation W1433572951 @default.
- W143357295 hasLocation W1433572952 @default.
- W143357295 hasLocation W1433572953 @default.
- W143357295 hasOpenAccess W143357295 @default.
- W143357295 hasPrimaryLocation W1433572951 @default.
- W143357295 hasRelatedWork W1596801655 @default.
- W143357295 hasRelatedWork W2130043461 @default.
- W143357295 hasRelatedWork W2350741829 @default.
- W143357295 hasRelatedWork W2358668433 @default.
- W143357295 hasRelatedWork W2376932109 @default.
- W143357295 hasRelatedWork W2382290278 @default.
- W143357295 hasRelatedWork W2390279801 @default.
- W143357295 hasRelatedWork W2748952813 @default.
- W143357295 hasRelatedWork W2899084033 @default.
- W143357295 hasRelatedWork W2530322880 @default.
- W143357295 isParatext "false" @default.
- W143357295 isRetracted "false" @default.
- W143357295 magId "143357295" @default.
- W143357295 workType "book-chapter" @default.