Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380433660> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W4380433660 abstract "Recent advancements in image sensor technology and deep learning have led to increased expectations for improving object detection performance in EO/IR systems. However, the large-scale datasets made available for deep learning model training exhibit significant differences in data distribution compared to the multispectral images acquired from the actual target domain, EO/IR systems. Because of this, when a pretrained deep-learning model is applied to real-world issues for multispectral object detection, it does not work well for inputs with a different distribution from a training dataset. Therefore, a dataset for additional fine-tuning is required. However, labeled datasets required for retraining can be challenging to acquire in practice because of security issues and high acquisition costs. These domain differences and dataset issues are crucial challenges concerning the use of AI in military applications. We herein propose an unsupervised domain adaptation method for object detection in multispectral images with domain discrepancies with a pretrained model on a large public dataset. We train an encoder network without direct labeling to generate feature maps similar to the backbone applied to existing detectors. The proposed approach has the advantage of being able to directly utilize pretrained object detection models from large-scale public datasets by simply training the encoder network alone." @default.
- W4380433660 created "2023-06-14" @default.
- W4380433660 creator A5031393194 @default.
- W4380433660 creator A5049079358 @default.
- W4380433660 creator A5083639385 @default.
- W4380433660 creator A5084922878 @default.
- W4380433660 creator A5092150673 @default.
- W4380433660 date "2023-06-13" @default.
- W4380433660 modified "2023-09-25" @default.
- W4380433660 title "Unsupervised domain adaptation for multispectral object detection" @default.
- W4380433660 doi "https://doi.org/10.1117/12.2664074" @default.
- W4380433660 hasPublicationYear "2023" @default.
- W4380433660 type Work @default.
- W4380433660 citedByCount "0" @default.
- W4380433660 crossrefType "proceedings-article" @default.
- W4380433660 hasAuthorship W4380433660A5031393194 @default.
- W4380433660 hasAuthorship W4380433660A5049079358 @default.
- W4380433660 hasAuthorship W4380433660A5083639385 @default.
- W4380433660 hasAuthorship W4380433660A5084922878 @default.
- W4380433660 hasAuthorship W4380433660A5092150673 @default.
- W4380433660 hasConcept C108583219 @default.
- W4380433660 hasConcept C111919701 @default.
- W4380433660 hasConcept C118505674 @default.
- W4380433660 hasConcept C119857082 @default.
- W4380433660 hasConcept C120665830 @default.
- W4380433660 hasConcept C121332964 @default.
- W4380433660 hasConcept C134306372 @default.
- W4380433660 hasConcept C138885662 @default.
- W4380433660 hasConcept C139807058 @default.
- W4380433660 hasConcept C153180895 @default.
- W4380433660 hasConcept C154945302 @default.
- W4380433660 hasConcept C173163844 @default.
- W4380433660 hasConcept C2776151529 @default.
- W4380433660 hasConcept C2776401178 @default.
- W4380433660 hasConcept C2781238097 @default.
- W4380433660 hasConcept C31972630 @default.
- W4380433660 hasConcept C33923547 @default.
- W4380433660 hasConcept C36503486 @default.
- W4380433660 hasConcept C41008148 @default.
- W4380433660 hasConcept C41895202 @default.
- W4380433660 hasConceptScore W4380433660C108583219 @default.
- W4380433660 hasConceptScore W4380433660C111919701 @default.
- W4380433660 hasConceptScore W4380433660C118505674 @default.
- W4380433660 hasConceptScore W4380433660C119857082 @default.
- W4380433660 hasConceptScore W4380433660C120665830 @default.
- W4380433660 hasConceptScore W4380433660C121332964 @default.
- W4380433660 hasConceptScore W4380433660C134306372 @default.
- W4380433660 hasConceptScore W4380433660C138885662 @default.
- W4380433660 hasConceptScore W4380433660C139807058 @default.
- W4380433660 hasConceptScore W4380433660C153180895 @default.
- W4380433660 hasConceptScore W4380433660C154945302 @default.
- W4380433660 hasConceptScore W4380433660C173163844 @default.
- W4380433660 hasConceptScore W4380433660C2776151529 @default.
- W4380433660 hasConceptScore W4380433660C2776401178 @default.
- W4380433660 hasConceptScore W4380433660C2781238097 @default.
- W4380433660 hasConceptScore W4380433660C31972630 @default.
- W4380433660 hasConceptScore W4380433660C33923547 @default.
- W4380433660 hasConceptScore W4380433660C36503486 @default.
- W4380433660 hasConceptScore W4380433660C41008148 @default.
- W4380433660 hasConceptScore W4380433660C41895202 @default.
- W4380433660 hasLocation W43804336601 @default.
- W4380433660 hasOpenAccess W4380433660 @default.
- W4380433660 hasPrimaryLocation W43804336601 @default.
- W4380433660 hasRelatedWork W1971759388 @default.
- W4380433660 hasRelatedWork W2007544051 @default.
- W4380433660 hasRelatedWork W2021186063 @default.
- W4380433660 hasRelatedWork W2025800131 @default.
- W4380433660 hasRelatedWork W2035456249 @default.
- W4380433660 hasRelatedWork W2095705906 @default.
- W4380433660 hasRelatedWork W2129974284 @default.
- W4380433660 hasRelatedWork W2922421953 @default.
- W4380433660 hasRelatedWork W2970686063 @default.
- W4380433660 hasRelatedWork W2975200075 @default.
- W4380433660 isParatext "false" @default.
- W4380433660 isRetracted "false" @default.
- W4380433660 workType "article" @default.