Matches in SemOpenAlex for { <https://semopenalex.org/work/W3169879351> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W3169879351 abstract "While recent studies on semi-supervised learning have shown remarkable progress in leveraging both labeled and unlabeled data, most of them presume a basic setting of the model is randomly initialized. In this work, we consider semi-supervised learning and transfer learning jointly, leading to a more practical and competitive paradigm that can utilize both powerful pre-trained models from source domain as well as labeled/unlabeled data in the target domain. To better exploit the value of both pre-trained weights and unlabeled target examples, we introduce adaptive consistency regularization that consists of two complementary components: Adaptive Knowledge Consistency (AKC) on the examples between the source and target model, and Adaptive Representation Consistency (ARC) on the target model between labeled and unlabeled examples. Examples involved in the consistency regularization are adaptively selected according to their potential contributions to the target task. We conduct extensive experiments on popular benchmarks including CIFAR-10, CUB-200, and MURA, by fine-tuning the ImageNet pre-trained ResNet-50 model. Results show that our proposed adaptive consistency regularization outperforms state-of-the-art semi-supervised learning techniques such as Pseudo Label, Mean Teacher, and FixMatch. Moreover, our algorithm is orthogonal to existing methods and thus able to gain additional improvements on top of MixMatch and FixMatch. Our code is available at https://github.com/Walleclipse/Semi-Supervised-Transfer-Learning-Paddle." @default.
- W3169879351 created "2021-06-22" @default.
- W3169879351 creator A5002072267 @default.
- W3169879351 creator A5007257165 @default.
- W3169879351 creator A5021332177 @default.
- W3169879351 creator A5064613859 @default.
- W3169879351 creator A5084125013 @default.
- W3169879351 date "2021-06-01" @default.
- W3169879351 modified "2023-10-10" @default.
- W3169879351 title "Adaptive Consistency Regularization for Semi-Supervised Transfer Learning" @default.
- W3169879351 cites W2108561737 @default.
- W3169879351 cites W2108598243 @default.
- W3169879351 cites W2115403315 @default.
- W3169879351 cites W2152161678 @default.
- W3169879351 cites W2164943005 @default.
- W3169879351 cites W2165698076 @default.
- W3169879351 cites W2194775991 @default.
- W3169879351 cites W2296073425 @default.
- W3169879351 cites W2473930607 @default.
- W3169879351 cites W2591924527 @default.
- W3169879351 cites W2796346823 @default.
- W3169879351 cites W2798381792 @default.
- W3169879351 cites W2963460174 @default.
- W3169879351 cites W2963614071 @default.
- W3169879351 cites W2963878020 @default.
- W3169879351 cites W2964137095 @default.
- W3169879351 cites W2988852559 @default.
- W3169879351 cites W2991719956 @default.
- W3169879351 cites W3003448987 @default.
- W3169879351 cites W3034453888 @default.
- W3169879351 cites W3034590424 @default.
- W3169879351 cites W4255421341 @default.
- W3169879351 doi "https://doi.org/10.1109/cvpr46437.2021.00685" @default.
- W3169879351 hasPublicationYear "2021" @default.
- W3169879351 type Work @default.
- W3169879351 sameAs 3169879351 @default.
- W3169879351 citedByCount "32" @default.
- W3169879351 countsByYear W31698793512021 @default.
- W3169879351 countsByYear W31698793512022 @default.
- W3169879351 countsByYear W31698793512023 @default.
- W3169879351 crossrefType "proceedings-article" @default.
- W3169879351 hasAuthorship W3169879351A5002072267 @default.
- W3169879351 hasAuthorship W3169879351A5007257165 @default.
- W3169879351 hasAuthorship W3169879351A5021332177 @default.
- W3169879351 hasAuthorship W3169879351A5064613859 @default.
- W3169879351 hasAuthorship W3169879351A5084125013 @default.
- W3169879351 hasBestOaLocation W31698793512 @default.
- W3169879351 hasConcept C111919701 @default.
- W3169879351 hasConcept C119857082 @default.
- W3169879351 hasConcept C150899416 @default.
- W3169879351 hasConcept C153180895 @default.
- W3169879351 hasConcept C154945302 @default.
- W3169879351 hasConcept C165696696 @default.
- W3169879351 hasConcept C2776135515 @default.
- W3169879351 hasConcept C2776145971 @default.
- W3169879351 hasConcept C2776436953 @default.
- W3169879351 hasConcept C38652104 @default.
- W3169879351 hasConcept C41008148 @default.
- W3169879351 hasConcept C43126263 @default.
- W3169879351 hasConcept C58973888 @default.
- W3169879351 hasConceptScore W3169879351C111919701 @default.
- W3169879351 hasConceptScore W3169879351C119857082 @default.
- W3169879351 hasConceptScore W3169879351C150899416 @default.
- W3169879351 hasConceptScore W3169879351C153180895 @default.
- W3169879351 hasConceptScore W3169879351C154945302 @default.
- W3169879351 hasConceptScore W3169879351C165696696 @default.
- W3169879351 hasConceptScore W3169879351C2776135515 @default.
- W3169879351 hasConceptScore W3169879351C2776145971 @default.
- W3169879351 hasConceptScore W3169879351C2776436953 @default.
- W3169879351 hasConceptScore W3169879351C38652104 @default.
- W3169879351 hasConceptScore W3169879351C41008148 @default.
- W3169879351 hasConceptScore W3169879351C43126263 @default.
- W3169879351 hasConceptScore W3169879351C58973888 @default.
- W3169879351 hasFunder F4320321655 @default.
- W3169879351 hasLocation W31698793511 @default.
- W3169879351 hasLocation W31698793512 @default.
- W3169879351 hasOpenAccess W3169879351 @default.
- W3169879351 hasPrimaryLocation W31698793511 @default.
- W3169879351 hasRelatedWork W2951234401 @default.
- W3169879351 hasRelatedWork W2991719956 @default.
- W3169879351 hasRelatedWork W3017346530 @default.
- W3169879351 hasRelatedWork W3017361373 @default.
- W3169879351 hasRelatedWork W3099805903 @default.
- W3169879351 hasRelatedWork W3134919356 @default.
- W3169879351 hasRelatedWork W3169879351 @default.
- W3169879351 hasRelatedWork W3195062561 @default.
- W3169879351 hasRelatedWork W4288376383 @default.
- W3169879351 hasRelatedWork W4361193208 @default.
- W3169879351 isParatext "false" @default.
- W3169879351 isRetracted "false" @default.
- W3169879351 magId "3169879351" @default.
- W3169879351 workType "article" @default.