Matches in SemOpenAlex for { <https://semopenalex.org/work/W4283770197> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W4283770197 abstract "Detection models trained by one party (including server) may face severe performance degradation when distributed to other users (clients). Federated learning can enable multi-party collaborative learning without leaking client data. In this paper, we focus on a special cross-domain scenario in which the server has large-scale labeled data and multiple clients only have a small amount of labeled data; meanwhile, there exist differences in data distributions among the clients. In this case, traditional federated learning methods can't help a client learn both the global knowledge of all participants and its own unique knowledge. To make up for this limitation, we propose a cross-domain federated object detection framework, named FedOD. The proposed framework first performs the federated training to obtain a public global aggregated model through multi-teacher distillation, and sends the aggregated model back to each client for fine-tuning its personalized local model. After a few rounds of communication, on each client we can perform weighted ensemble inference on the public global model and the personalized local model. We establish a federated object detection dataset which has significant background differences and instance differences based on multiple public autonomous driving datasets, and then conduct extensive experiments on the dataset. The experimental results validate the effectiveness of the proposed method." @default.
- W4283770197 created "2022-07-03" @default.
- W4283770197 creator A5003418019 @default.
- W4283770197 creator A5005344729 @default.
- W4283770197 creator A5029695887 @default.
- W4283770197 creator A5056318061 @default.
- W4283770197 creator A5059977860 @default.
- W4283770197 date "2022-06-29" @default.
- W4283770197 modified "2023-09-26" @default.
- W4283770197 title "Cross-domain Federated Object Detection" @default.
- W4283770197 doi "https://doi.org/10.1109/icme55011.2023.00254" @default.
- W4283770197 hasPublicationYear "2022" @default.
- W4283770197 type Work @default.
- W4283770197 citedByCount "0" @default.
- W4283770197 crossrefType "posted-content" @default.
- W4283770197 hasAuthorship W4283770197A5003418019 @default.
- W4283770197 hasAuthorship W4283770197A5005344729 @default.
- W4283770197 hasAuthorship W4283770197A5029695887 @default.
- W4283770197 hasAuthorship W4283770197A5056318061 @default.
- W4283770197 hasAuthorship W4283770197A5059977860 @default.
- W4283770197 hasBestOaLocation W42837701971 @default.
- W4283770197 hasConcept C119857082 @default.
- W4283770197 hasConcept C120665830 @default.
- W4283770197 hasConcept C121332964 @default.
- W4283770197 hasConcept C124101348 @default.
- W4283770197 hasConcept C134306372 @default.
- W4283770197 hasConcept C138885662 @default.
- W4283770197 hasConcept C153180895 @default.
- W4283770197 hasConcept C154945302 @default.
- W4283770197 hasConcept C192209626 @default.
- W4283770197 hasConcept C27206212 @default.
- W4283770197 hasConcept C2776151529 @default.
- W4283770197 hasConcept C2776214188 @default.
- W4283770197 hasConcept C2781238097 @default.
- W4283770197 hasConcept C2992525071 @default.
- W4283770197 hasConcept C33923547 @default.
- W4283770197 hasConcept C36503486 @default.
- W4283770197 hasConcept C41008148 @default.
- W4283770197 hasConcept C512654426 @default.
- W4283770197 hasConceptScore W4283770197C119857082 @default.
- W4283770197 hasConceptScore W4283770197C120665830 @default.
- W4283770197 hasConceptScore W4283770197C121332964 @default.
- W4283770197 hasConceptScore W4283770197C124101348 @default.
- W4283770197 hasConceptScore W4283770197C134306372 @default.
- W4283770197 hasConceptScore W4283770197C138885662 @default.
- W4283770197 hasConceptScore W4283770197C153180895 @default.
- W4283770197 hasConceptScore W4283770197C154945302 @default.
- W4283770197 hasConceptScore W4283770197C192209626 @default.
- W4283770197 hasConceptScore W4283770197C27206212 @default.
- W4283770197 hasConceptScore W4283770197C2776151529 @default.
- W4283770197 hasConceptScore W4283770197C2776214188 @default.
- W4283770197 hasConceptScore W4283770197C2781238097 @default.
- W4283770197 hasConceptScore W4283770197C2992525071 @default.
- W4283770197 hasConceptScore W4283770197C33923547 @default.
- W4283770197 hasConceptScore W4283770197C36503486 @default.
- W4283770197 hasConceptScore W4283770197C41008148 @default.
- W4283770197 hasConceptScore W4283770197C512654426 @default.
- W4283770197 hasLocation W42837701971 @default.
- W4283770197 hasOpenAccess W4283770197 @default.
- W4283770197 hasPrimaryLocation W42837701971 @default.
- W4283770197 hasRelatedWork W1988485990 @default.
- W4283770197 hasRelatedWork W2007544051 @default.
- W4283770197 hasRelatedWork W2095705906 @default.
- W4283770197 hasRelatedWork W2127769904 @default.
- W4283770197 hasRelatedWork W2801801420 @default.
- W4283770197 hasRelatedWork W2970686063 @default.
- W4283770197 hasRelatedWork W2975200075 @default.
- W4283770197 hasRelatedWork W3187859696 @default.
- W4283770197 hasRelatedWork W4221040873 @default.
- W4283770197 hasRelatedWork W4286543385 @default.
- W4283770197 isParatext "false" @default.
- W4283770197 isRetracted "false" @default.
- W4283770197 workType "article" @default.