FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4376954717> ?p ?o ?g. }

• W4376954717 endingPage "2584" @default.
• W4376954717 startingPage "2584" @default.
• W4376954717 abstract "Automated inspection systems utilizing computer vision technology are effective in managing traffic control devices (TCDs); however, they face challenges due to the limited availability of training datasets and the difficulty in generating new datasets. To address this, our study establishes a benchmark for cost-effective model training methods that achieve the desired accuracy using data from related domains and YOLOv5, a one-stage object detector known for its high accuracy and speed. In this study, three model cases were developed using distinct training approaches: (1) training with COCO-based pre-trained weights, (2) training with pre-trained weights from the source domain, and (3) training with a synthesized dataset mixed with source and target domains. Upon comparing these model cases, this study found that directly applying source domain data to the target domain is unfeasible, and a small amount of target domain data is necessary for optimal performance. A model trained with fine-tuning-based domain adaptation using pre-trained weights from the source domain and minimal target data, proved to be the most resource-efficient approach. These results contribute valuable guidance for practitioners aiming to develop TCD models with limited data, enabling them to build optimal models while conserving resources." @default.
• W4376954717 created "2023-05-18" @default.
• W4376954717 creator A5003141456 @default.
• W4376954717 creator A5007541279 @default.
• W4376954717 creator A5008088400 @default.
• W4376954717 creator A5048443039 @default.
• W4376954717 creator A5059716746 @default.
• W4376954717 creator A5067305497 @default.
• W4376954717 creator A5084038059 @default.
• W4376954717 creator A5084241240 @default.
• W4376954717 date "2023-05-15" @default.
• W4376954717 modified "2023-09-27" @default.
• W4376954717 title "Low-Cost Object Detection Models for Traffic Control Devices through Domain Adaption of Geographical Regions" @default.
• W4376954717 cites W1566134554 @default.
• W4376954717 cites W1978736542 @default.
• W4376954717 cites W2008635359 @default.
• W4376954717 cites W2109255472 @default.
• W4376954717 cites W2117876524 @default.
• W4376954717 cites W2159570078 @default.
• W4376954717 cites W2165698076 @default.
• W4376954717 cites W2346062110 @default.
• W4376954717 cites W2479866714 @default.
• W4376954717 cites W2756202949 @default.
• W4376954717 cites W2786808285 @default.
• W4376954717 cites W2803862859 @default.
• W4376954717 cites W2952113774 @default.
• W4376954717 cites W2962843773 @default.
• W4376954717 cites W2963460174 @default.
• W4376954717 cites W2963877604 @default.
• W4376954717 cites W2970212581 @default.
• W4376954717 cites W2992240579 @default.
• W4376954717 cites W3010381534 @default.
• W4376954717 cites W3011707748 @default.
• W4376954717 cites W3041133507 @default.
• W4376954717 cites W3043995050 @default.
• W4376954717 cites W3048378273 @default.
• W4376954717 cites W3080355920 @default.
• W4376954717 cites W3081899694 @default.
• W4376954717 cites W3090532574 @default.
• W4376954717 cites W3091322135 @default.
• W4376954717 cites W3094277917 @default.
• W4376954717 cites W3095701251 @default.
• W4376954717 cites W3108586519 @default.
• W4376954717 cites W3122279293 @default.
• W4376954717 cites W3124372372 @default.
• W4376954717 cites W3159196909 @default.
• W4376954717 cites W3193307590 @default.
• W4376954717 cites W3198684591 @default.
• W4376954717 cites W3201064488 @default.
• W4376954717 cites W3204444155 @default.
• W4376954717 cites W3210672387 @default.
• W4376954717 cites W4210394625 @default.
• W4376954717 cites W4213218297 @default.
• W4376954717 cites W4213267140 @default.
• W4376954717 cites W4220773165 @default.
• W4376954717 cites W4220861084 @default.
• W4376954717 cites W4283761765 @default.
• W4376954717 cites W4285107929 @default.
• W4376954717 cites W4293083414 @default.
• W4376954717 cites W4293764610 @default.
• W4376954717 cites W4312183515 @default.
• W4376954717 doi "https://doi.org/10.3390/rs15102584" @default.
• W4376954717 hasPublicationYear "2023" @default.
• W4376954717 type Work @default.
• W4376954717 citedByCount "0" @default.
• W4376954717 crossrefType "journal-article" @default.
• W4376954717 hasAuthorship W4376954717A5003141456 @default.
• W4376954717 hasAuthorship W4376954717A5007541279 @default.
• W4376954717 hasAuthorship W4376954717A5008088400 @default.
• W4376954717 hasAuthorship W4376954717A5048443039 @default.
• W4376954717 hasAuthorship W4376954717A5059716746 @default.
• W4376954717 hasAuthorship W4376954717A5067305497 @default.
• W4376954717 hasAuthorship W4376954717A5084038059 @default.
• W4376954717 hasAuthorship W4376954717A5084241240 @default.
• W4376954717 hasBestOaLocation W43769547171 @default.
• W4376954717 hasConcept C119857082 @default.
• W4376954717 hasConcept C121332964 @default.
• W4376954717 hasConcept C124101348 @default.
• W4376954717 hasConcept C13280743 @default.
• W4376954717 hasConcept C134306372 @default.
• W4376954717 hasConcept C153180895 @default.
• W4376954717 hasConcept C153294291 @default.
• W4376954717 hasConcept C154945302 @default.
• W4376954717 hasConcept C185798385 @default.
• W4376954717 hasConcept C205649164 @default.
• W4376954717 hasConcept C206345919 @default.
• W4376954717 hasConcept C2776151529 @default.
• W4376954717 hasConcept C2776434776 @default.
• W4376954717 hasConcept C2777211547 @default.
• W4376954717 hasConcept C31258907 @default.
• W4376954717 hasConcept C33923547 @default.
• W4376954717 hasConcept C36503486 @default.
• W4376954717 hasConcept C41008148 @default.
• W4376954717 hasConcept C51632099 @default.
• W4376954717 hasConcept C95623464 @default.
• W4376954717 hasConceptScore W4376954717C119857082 @default.
• W4376954717 hasConceptScore W4376954717C121332964 @default.
• W4376954717 hasConceptScore W4376954717C124101348 @default.

• next