Matches in SemOpenAlex for { <https://semopenalex.org/work/W3205764392> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W3205764392 abstract "With significant advances in deep learning, many computer vision applications have reached the inflection point. However, these deep learning models need large amount of labeled data for model training and optimum parameter estimation. Limited labeled data for model training results in overfitting and impacts their generalization performance. However, the collection and annotation of large amount of data is a very time consuming and expensive operation. Further, due to privacy and security concerns, the large amount of labeled data could not be collected for certain applications such as those involving medical field. Self-training, Co-training, and Self-ensemble methods are three types of semi-supervised learning methods that can be used to exploit unlabeled data. In this paper, we propose self-ensemble based deep learning model that along with limited labeled data, harness unlabeled data for improving the generalization performance. We evaluated the proposed self-ensemble based deep-learning model for soft-biometric gender and age classification. Experimental evaluation on CelebA and VISO B datasets suggest gender classification accuracy of 94.46 % and 81.00 %, respectively, using only 1000 labeled samples and remaining 199k samples as unlabeled samples for CelebA dataset and similarly,1000 labeled samples with remaining 107k samples as unlabeled samples for VISOB dataset. Comparative evaluation suggest that there is 5.74% and 8.47% improvement in the accuracy of the self-ensemble model when compared with supervised model trained on the entire CelebA and VISOB dataset, respectively. We also evaluated the proposed learning method for age-group prediction on Adience dataset and it outperformed the baseline supervised deep-learning learning model with a better exact accuracy of 55.55 ± 4.28 which is 3.92% more than the baseline." @default.
- W3205764392 created "2021-10-25" @default.
- W3205764392 creator A5013534765 @default.
- W3205764392 creator A5013687277 @default.
- W3205764392 creator A5015607309 @default.
- W3205764392 creator A5081904333 @default.
- W3205764392 date "2021-12-05" @default.
- W3205764392 modified "2023-09-26" @default.
- W3205764392 title "Harnessing Unlabeled Data to Improve Generalization of Biometric Gender and Age Classifiers" @default.
- W3205764392 cites W1834627138 @default.
- W3205764392 cites W1905153633 @default.
- W3205764392 cites W1965804146 @default.
- W3205764392 cites W2052294358 @default.
- W3205764392 cites W2077265636 @default.
- W3205764392 cites W2118314245 @default.
- W3205764392 cites W2126475620 @default.
- W3205764392 cites W2130352044 @default.
- W3205764392 cites W2140797539 @default.
- W3205764392 cites W2237515533 @default.
- W3205764392 cites W2517157101 @default.
- W3205764392 cites W2600148249 @default.
- W3205764392 cites W2617023900 @default.
- W3205764392 cites W2786753095 @default.
- W3205764392 cites W2793708128 @default.
- W3205764392 cites W2794386855 @default.
- W3205764392 cites W2847300371 @default.
- W3205764392 cites W2913662957 @default.
- W3205764392 cites W2931490846 @default.
- W3205764392 cites W2963266717 @default.
- W3205764392 cites W2963326042 @default.
- W3205764392 cites W297909767 @default.
- W3205764392 cites W3133226796 @default.
- W3205764392 doi "https://doi.org/10.1109/ssci50451.2021.9660182" @default.
- W3205764392 hasPublicationYear "2021" @default.
- W3205764392 type Work @default.
- W3205764392 sameAs 3205764392 @default.
- W3205764392 citedByCount "2" @default.
- W3205764392 countsByYear W32057643922022 @default.
- W3205764392 countsByYear W32057643922023 @default.
- W3205764392 crossrefType "proceedings-article" @default.
- W3205764392 hasAuthorship W3205764392A5013534765 @default.
- W3205764392 hasAuthorship W3205764392A5013687277 @default.
- W3205764392 hasAuthorship W3205764392A5015607309 @default.
- W3205764392 hasAuthorship W3205764392A5081904333 @default.
- W3205764392 hasBestOaLocation W32057643922 @default.
- W3205764392 hasConcept C108583219 @default.
- W3205764392 hasConcept C119857082 @default.
- W3205764392 hasConcept C134306372 @default.
- W3205764392 hasConcept C136389625 @default.
- W3205764392 hasConcept C153180895 @default.
- W3205764392 hasConcept C154945302 @default.
- W3205764392 hasConcept C177148314 @default.
- W3205764392 hasConcept C184297639 @default.
- W3205764392 hasConcept C202444582 @default.
- W3205764392 hasConcept C22019652 @default.
- W3205764392 hasConcept C2776145971 @default.
- W3205764392 hasConcept C33923547 @default.
- W3205764392 hasConcept C41008148 @default.
- W3205764392 hasConcept C45942800 @default.
- W3205764392 hasConcept C50644808 @default.
- W3205764392 hasConcept C51632099 @default.
- W3205764392 hasConcept C58973888 @default.
- W3205764392 hasConcept C9652623 @default.
- W3205764392 hasConceptScore W3205764392C108583219 @default.
- W3205764392 hasConceptScore W3205764392C119857082 @default.
- W3205764392 hasConceptScore W3205764392C134306372 @default.
- W3205764392 hasConceptScore W3205764392C136389625 @default.
- W3205764392 hasConceptScore W3205764392C153180895 @default.
- W3205764392 hasConceptScore W3205764392C154945302 @default.
- W3205764392 hasConceptScore W3205764392C177148314 @default.
- W3205764392 hasConceptScore W3205764392C184297639 @default.
- W3205764392 hasConceptScore W3205764392C202444582 @default.
- W3205764392 hasConceptScore W3205764392C22019652 @default.
- W3205764392 hasConceptScore W3205764392C2776145971 @default.
- W3205764392 hasConceptScore W3205764392C33923547 @default.
- W3205764392 hasConceptScore W3205764392C41008148 @default.
- W3205764392 hasConceptScore W3205764392C45942800 @default.
- W3205764392 hasConceptScore W3205764392C50644808 @default.
- W3205764392 hasConceptScore W3205764392C51632099 @default.
- W3205764392 hasConceptScore W3205764392C58973888 @default.
- W3205764392 hasConceptScore W3205764392C9652623 @default.
- W3205764392 hasLocation W32057643921 @default.
- W3205764392 hasLocation W32057643922 @default.
- W3205764392 hasOpenAccess W3205764392 @default.
- W3205764392 hasPrimaryLocation W32057643921 @default.
- W3205764392 hasRelatedWork W1473009882 @default.
- W3205764392 hasRelatedWork W2053559602 @default.
- W3205764392 hasRelatedWork W2604407846 @default.
- W3205764392 hasRelatedWork W3099765033 @default.
- W3205764392 hasRelatedWork W3119385233 @default.
- W3205764392 hasRelatedWork W4306904961 @default.
- W3205764392 hasRelatedWork W4312414840 @default.
- W3205764392 hasRelatedWork W4318825627 @default.
- W3205764392 hasRelatedWork W4319309271 @default.
- W3205764392 hasRelatedWork W4385422125 @default.
- W3205764392 isParatext "false" @default.
- W3205764392 isRetracted "false" @default.
- W3205764392 magId "3205764392" @default.
- W3205764392 workType "article" @default.