Matches in SemOpenAlex for { <https://semopenalex.org/work/W3024571412> ?p ?o ?g. }
- W3024571412 abstract "Currently, the divergence in distributions of design and operational data, and large computational complexity are limiting factors in the adoption of CNNs in real-world applications. For instance, person re-identification systems typically rely on a distributed set of cameras, where each camera has different capture conditions. This can translate to a considerable shift between source (e.g. lab setting) and target (e.g. operational camera) domains. Given the cost of annotating image data captured for fine-tuning in each target domain, unsupervised domain adaptation (UDA) has become a popular approach to adapt CNNs. Moreover, state-of-the-art deep learning models that provide a high level of accuracy often rely on architectures that are too complex for real-time applications. Although several compression and UDA approaches have recently been proposed to overcome these limitations, they do not allow optimizing a CNN to simultaneously address both. In this paper, we propose an unexplored direction -- the joint optimization of CNNs to provide a compressed model that is adapted to perform well for a given target domain. In particular, the proposed approach performs unsupervised knowledge distillation (KD) from a complex teacher model to a compact student model, by leveraging both source and target data. It also improves upon existing UDA techniques by progressively teaching the student about domain-invariant features, instead of directly adapting a compact model on target domain data. Our method is compared against state-of-the-art compression and UDA techniques, using two popular classification datasets for UDA -- Office31 and ImageClef-DA. In both datasets, results indicate that our method can achieve the highest level of accuracy while requiring a comparable or lower time complexity." @default.
- W3024571412 created "2020-05-21" @default.
- W3024571412 creator A5004770604 @default.
- W3024571412 creator A5006937759 @default.
- W3024571412 creator A5022943037 @default.
- W3024571412 creator A5032176624 @default.
- W3024571412 creator A5046794574 @default.
- W3024571412 date "2020-05-16" @default.
- W3024571412 modified "2023-09-27" @default.
- W3024571412 title "Joint Progressive Knowledge Distillation and Unsupervised Domain Adaptation" @default.
- W3024571412 cites W1821462560 @default.
- W3024571412 cites W1882958252 @default.
- W3024571412 cites W2159291411 @default.
- W3024571412 cites W2584009249 @default.
- W3024571412 cites W2586087033 @default.
- W3024571412 cites W2593768305 @default.
- W3024571412 cites W2594718649 @default.
- W3024571412 cites W2605135468 @default.
- W3024571412 cites W2783538964 @default.
- W3024571412 cites W2786808285 @default.
- W3024571412 cites W2798964604 @default.
- W3024571412 cites W2894043696 @default.
- W3024571412 cites W2896409484 @default.
- W3024571412 cites W2904923893 @default.
- W3024571412 cites W2911803042 @default.
- W3024571412 cites W2926595253 @default.
- W3024571412 cites W2928560789 @default.
- W3024571412 cites W2950967261 @default.
- W3024571412 cites W2952243440 @default.
- W3024571412 cites W2953875771 @default.
- W3024571412 cites W2962808524 @default.
- W3024571412 cites W2962964479 @default.
- W3024571412 cites W2963113185 @default.
- W3024571412 cites W2963140444 @default.
- W3024571412 cites W2963150697 @default.
- W3024571412 cites W2963813662 @default.
- W3024571412 cites W2964019233 @default.
- W3024571412 cites W2964264300 @default.
- W3024571412 cites W2964299589 @default.
- W3024571412 cites W2965862774 @default.
- W3024571412 cites W2969520366 @default.
- W3024571412 cites W2970330753 @default.
- W3024571412 cites W2970790493 @default.
- W3024571412 cites W2982157312 @default.
- W3024571412 cites W2996390082 @default.
- W3024571412 cites W2997972888 @default.
- W3024571412 cites W2976122994 @default.
- W3024571412 hasPublicationYear "2020" @default.
- W3024571412 type Work @default.
- W3024571412 sameAs 3024571412 @default.
- W3024571412 citedByCount "0" @default.
- W3024571412 crossrefType "posted-content" @default.
- W3024571412 hasAuthorship W3024571412A5004770604 @default.
- W3024571412 hasAuthorship W3024571412A5006937759 @default.
- W3024571412 hasAuthorship W3024571412A5022943037 @default.
- W3024571412 hasAuthorship W3024571412A5032176624 @default.
- W3024571412 hasAuthorship W3024571412A5046794574 @default.
- W3024571412 hasConcept C119857082 @default.
- W3024571412 hasConcept C124101348 @default.
- W3024571412 hasConcept C127413603 @default.
- W3024571412 hasConcept C134306372 @default.
- W3024571412 hasConcept C138885662 @default.
- W3024571412 hasConcept C153180895 @default.
- W3024571412 hasConcept C154945302 @default.
- W3024571412 hasConcept C170154142 @default.
- W3024571412 hasConcept C177264268 @default.
- W3024571412 hasConcept C18555067 @default.
- W3024571412 hasConcept C199360897 @default.
- W3024571412 hasConcept C207390915 @default.
- W3024571412 hasConcept C2776434776 @default.
- W3024571412 hasConcept C33923547 @default.
- W3024571412 hasConcept C36503486 @default.
- W3024571412 hasConcept C41008148 @default.
- W3024571412 hasConcept C41895202 @default.
- W3024571412 hasConcept C95623464 @default.
- W3024571412 hasConceptScore W3024571412C119857082 @default.
- W3024571412 hasConceptScore W3024571412C124101348 @default.
- W3024571412 hasConceptScore W3024571412C127413603 @default.
- W3024571412 hasConceptScore W3024571412C134306372 @default.
- W3024571412 hasConceptScore W3024571412C138885662 @default.
- W3024571412 hasConceptScore W3024571412C153180895 @default.
- W3024571412 hasConceptScore W3024571412C154945302 @default.
- W3024571412 hasConceptScore W3024571412C170154142 @default.
- W3024571412 hasConceptScore W3024571412C177264268 @default.
- W3024571412 hasConceptScore W3024571412C18555067 @default.
- W3024571412 hasConceptScore W3024571412C199360897 @default.
- W3024571412 hasConceptScore W3024571412C207390915 @default.
- W3024571412 hasConceptScore W3024571412C2776434776 @default.
- W3024571412 hasConceptScore W3024571412C33923547 @default.
- W3024571412 hasConceptScore W3024571412C36503486 @default.
- W3024571412 hasConceptScore W3024571412C41008148 @default.
- W3024571412 hasConceptScore W3024571412C41895202 @default.
- W3024571412 hasConceptScore W3024571412C95623464 @default.
- W3024571412 hasLocation W30245714121 @default.
- W3024571412 hasOpenAccess W3024571412 @default.
- W3024571412 hasPrimaryLocation W30245714121 @default.
- W3024571412 hasRelatedWork W2583503935 @default.
- W3024571412 hasRelatedWork W2794935216 @default.
- W3024571412 hasRelatedWork W2893671576 @default.
- W3024571412 hasRelatedWork W2902376486 @default.