Matches in SemOpenAlex for { <https://semopenalex.org/work/W4214529572> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W4214529572 endingPage "25507" @default.
- W4214529572 startingPage "25493" @default.
- W4214529572 abstract "To solve the problem that the feature maps generated by feature extraction network of traditional weakly supervised learning object detection algorithm is not strong in feature, and the mapping relationship between feature space and classification results is not strong, which restricts the performance of object detection, a weakly supervised object detection algorithm based on strong representation learning is proposed in this paper. Due to enhance the representation ability of feature maps, the algorithm weighted the channels of feature maps according to the importance of each channel, to strengthen the weight of crucial feature maps and ignore the significance of secondary feature maps. Meanwhile, a Gaussian Mixture distribution model with better classification performance was used to design the object instance classifier to enhance further the representation of the mapping between feature space and classification results, and a large-margin Gaussian Mixture (L-GM) loss was designed to increase the distance between sample categories and improve the generalization of the classifier. For verifying the effectiveness and advancement of the proposed algorithm, the performance of the proposed algorithm is compared with six classical weakly supervised target detection algorithms on VOC datasets. Experiments show that the weakly supervised target detection algorithm based on strong representation learning has outperformed other classical algorithms in average accuracy (AP) and correct location (CorLoc), with increases of 1.1%~14.6% and 2.8%~19.4%, respectively." @default.
- W4214529572 created "2022-03-02" @default.
- W4214529572 creator A5001189481 @default.
- W4214529572 creator A5008747201 @default.
- W4214529572 creator A5057575670 @default.
- W4214529572 creator A5076343685 @default.
- W4214529572 creator A5078208361 @default.
- W4214529572 creator A5079011877 @default.
- W4214529572 date "2022-02-01" @default.
- W4214529572 modified "2023-10-18" @default.
- W4214529572 title "Strong Representation Learning for Weakly Supervised Object Detection" @default.
- W4214529572 doi "https://doi.org/10.18535/ijecs/v11i02.4650" @default.
- W4214529572 hasPublicationYear "2022" @default.
- W4214529572 type Work @default.
- W4214529572 citedByCount "0" @default.
- W4214529572 crossrefType "journal-article" @default.
- W4214529572 hasAuthorship W4214529572A5001189481 @default.
- W4214529572 hasAuthorship W4214529572A5008747201 @default.
- W4214529572 hasAuthorship W4214529572A5057575670 @default.
- W4214529572 hasAuthorship W4214529572A5076343685 @default.
- W4214529572 hasAuthorship W4214529572A5078208361 @default.
- W4214529572 hasAuthorship W4214529572A5079011877 @default.
- W4214529572 hasBestOaLocation W42145295721 @default.
- W4214529572 hasConcept C119857082 @default.
- W4214529572 hasConcept C121332964 @default.
- W4214529572 hasConcept C136389625 @default.
- W4214529572 hasConcept C138885662 @default.
- W4214529572 hasConcept C139532973 @default.
- W4214529572 hasConcept C153180895 @default.
- W4214529572 hasConcept C154945302 @default.
- W4214529572 hasConcept C163716315 @default.
- W4214529572 hasConcept C17744445 @default.
- W4214529572 hasConcept C199539241 @default.
- W4214529572 hasConcept C2776151529 @default.
- W4214529572 hasConcept C2776359362 @default.
- W4214529572 hasConcept C2776401178 @default.
- W4214529572 hasConcept C41008148 @default.
- W4214529572 hasConcept C41895202 @default.
- W4214529572 hasConcept C50644808 @default.
- W4214529572 hasConcept C52622490 @default.
- W4214529572 hasConcept C59404180 @default.
- W4214529572 hasConcept C62520636 @default.
- W4214529572 hasConcept C774472 @default.
- W4214529572 hasConcept C83665646 @default.
- W4214529572 hasConcept C94625758 @default.
- W4214529572 hasConcept C95623464 @default.
- W4214529572 hasConceptScore W4214529572C119857082 @default.
- W4214529572 hasConceptScore W4214529572C121332964 @default.
- W4214529572 hasConceptScore W4214529572C136389625 @default.
- W4214529572 hasConceptScore W4214529572C138885662 @default.
- W4214529572 hasConceptScore W4214529572C139532973 @default.
- W4214529572 hasConceptScore W4214529572C153180895 @default.
- W4214529572 hasConceptScore W4214529572C154945302 @default.
- W4214529572 hasConceptScore W4214529572C163716315 @default.
- W4214529572 hasConceptScore W4214529572C17744445 @default.
- W4214529572 hasConceptScore W4214529572C199539241 @default.
- W4214529572 hasConceptScore W4214529572C2776151529 @default.
- W4214529572 hasConceptScore W4214529572C2776359362 @default.
- W4214529572 hasConceptScore W4214529572C2776401178 @default.
- W4214529572 hasConceptScore W4214529572C41008148 @default.
- W4214529572 hasConceptScore W4214529572C41895202 @default.
- W4214529572 hasConceptScore W4214529572C50644808 @default.
- W4214529572 hasConceptScore W4214529572C52622490 @default.
- W4214529572 hasConceptScore W4214529572C59404180 @default.
- W4214529572 hasConceptScore W4214529572C62520636 @default.
- W4214529572 hasConceptScore W4214529572C774472 @default.
- W4214529572 hasConceptScore W4214529572C83665646 @default.
- W4214529572 hasConceptScore W4214529572C94625758 @default.
- W4214529572 hasConceptScore W4214529572C95623464 @default.
- W4214529572 hasIssue "02" @default.
- W4214529572 hasLocation W42145295721 @default.
- W4214529572 hasOpenAccess W4214529572 @default.
- W4214529572 hasPrimaryLocation W42145295721 @default.
- W4214529572 hasRelatedWork W1595101524 @default.
- W4214529572 hasRelatedWork W1977222486 @default.
- W4214529572 hasRelatedWork W2049538278 @default.
- W4214529572 hasRelatedWork W2143407407 @default.
- W4214529572 hasRelatedWork W2368520799 @default.
- W4214529572 hasRelatedWork W2546942002 @default.
- W4214529572 hasRelatedWork W2592385986 @default.
- W4214529572 hasRelatedWork W2771515600 @default.
- W4214529572 hasRelatedWork W2772780115 @default.
- W4214529572 hasRelatedWork W2944661354 @default.
- W4214529572 hasVolume "11" @default.
- W4214529572 isParatext "false" @default.
- W4214529572 isRetracted "false" @default.
- W4214529572 workType "article" @default.