Matches in SemOpenAlex for { <https://semopenalex.org/work/W3203485385> ?p ?o ?g. }
- W3203485385 endingPage "3070" @default.
- W3203485385 startingPage "3058" @default.
- W3203485385 abstract "Object detection requires plentiful data annotated with bounding boxes for model training. However, in many applications, it is difficult or even impossible to acquire a large set of labeled examples for the target task due to the privacy concern or lack of reliable annotators. On the other hand, due to the high-quality image search engines, such as Flickr and Google, it is relatively easy to obtain resource-rich unlabeled datasets, whose categories are a superset of those of target data. In this article, to improve the target model with cost-effective supervision from source data, we propose a partial transfer learning approach QBox to actively query labels for bounding boxes of source images. Specifically, we design two criteria, i.e., informativeness and transferability, to measure the potential utility of a bounding box for improving the target model. Based on these criteria, QBox actively queries the labels of the most useful boxes from the source domain and, thus, requires fewer training examples to save the labeling cost. Furthermore, the proposed query strategy allows annotators to simply labeling a specific region, instead of the whole image, and, thus, significantly reduces the labeling difficulty. Extensive experiments are performed on various partial transfer benchmarks and a real COVID-19 detection task. The results validate that QBox improves the detection accuracy with lower labeling cost compared to state-of-the-art query strategies for object detection." @default.
- W3203485385 created "2021-10-11" @default.
- W3203485385 creator A5066964304 @default.
- W3203485385 creator A5069806977 @default.
- W3203485385 creator A5070740938 @default.
- W3203485385 creator A5079149569 @default.
- W3203485385 date "2023-06-01" @default.
- W3203485385 modified "2023-10-12" @default.
- W3203485385 title "QBox: Partial Transfer Learning With Active Querying for Object Detection" @default.
- W3203485385 cites W2012878613 @default.
- W3203485385 cites W2031489346 @default.
- W3203485385 cites W2150066425 @default.
- W3203485385 cites W2340897893 @default.
- W3203485385 cites W2408336333 @default.
- W3203485385 cites W2605343357 @default.
- W3203485385 cites W2608567823 @default.
- W3203485385 cites W2748021867 @default.
- W3203485385 cites W2786808285 @default.
- W3203485385 cites W2798587560 @default.
- W3203485385 cites W2808279896 @default.
- W3203485385 cites W2885722640 @default.
- W3203485385 cites W2904845482 @default.
- W3203485385 cites W2951671949 @default.
- W3203485385 cites W2955889502 @default.
- W3203485385 cites W2956371155 @default.
- W3203485385 cites W2962835731 @default.
- W3203485385 cites W2962986791 @default.
- W3203485385 cites W2963016543 @default.
- W3203485385 cites W2963351448 @default.
- W3203485385 cites W2963516811 @default.
- W3203485385 cites W2963978428 @default.
- W3203485385 cites W2964109570 @default.
- W3203485385 cites W2964115968 @default.
- W3203485385 cites W2964277612 @default.
- W3203485385 cites W2968634921 @default.
- W3203485385 cites W2981705647 @default.
- W3203485385 cites W2982770724 @default.
- W3203485385 cites W2984303785 @default.
- W3203485385 cites W2986514296 @default.
- W3203485385 cites W2988916019 @default.
- W3203485385 cites W2990069979 @default.
- W3203485385 cites W3035544567 @default.
- W3203485385 cites W3036403470 @default.
- W3203485385 cites W3041485444 @default.
- W3203485385 cites W3102701618 @default.
- W3203485385 cites W3106286224 @default.
- W3203485385 cites W3131350578 @default.
- W3203485385 cites W3131727177 @default.
- W3203485385 cites W3139487216 @default.
- W3203485385 doi "https://doi.org/10.1109/tnnls.2021.3111621" @default.
- W3203485385 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34570711" @default.
- W3203485385 hasPublicationYear "2023" @default.
- W3203485385 type Work @default.
- W3203485385 sameAs 3203485385 @default.
- W3203485385 citedByCount "3" @default.
- W3203485385 countsByYear W32034853852022 @default.
- W3203485385 countsByYear W32034853852023 @default.
- W3203485385 crossrefType "journal-article" @default.
- W3203485385 hasAuthorship W3203485385A5066964304 @default.
- W3203485385 hasAuthorship W3203485385A5069806977 @default.
- W3203485385 hasAuthorship W3203485385A5070740938 @default.
- W3203485385 hasAuthorship W3203485385A5079149569 @default.
- W3203485385 hasConcept C115961682 @default.
- W3203485385 hasConcept C119857082 @default.
- W3203485385 hasConcept C124101348 @default.
- W3203485385 hasConcept C134306372 @default.
- W3203485385 hasConcept C140331021 @default.
- W3203485385 hasConcept C147037132 @default.
- W3203485385 hasConcept C150899416 @default.
- W3203485385 hasConcept C153180895 @default.
- W3203485385 hasConcept C154945302 @default.
- W3203485385 hasConcept C162324750 @default.
- W3203485385 hasConcept C177264268 @default.
- W3203485385 hasConcept C187736073 @default.
- W3203485385 hasConcept C199360897 @default.
- W3203485385 hasConcept C23123220 @default.
- W3203485385 hasConcept C2776145971 @default.
- W3203485385 hasConcept C2776151529 @default.
- W3203485385 hasConcept C2780451532 @default.
- W3203485385 hasConcept C2781238097 @default.
- W3203485385 hasConcept C33923547 @default.
- W3203485385 hasConcept C36503486 @default.
- W3203485385 hasConcept C41008148 @default.
- W3203485385 hasConcept C61272859 @default.
- W3203485385 hasConcept C63584917 @default.
- W3203485385 hasConceptScore W3203485385C115961682 @default.
- W3203485385 hasConceptScore W3203485385C119857082 @default.
- W3203485385 hasConceptScore W3203485385C124101348 @default.
- W3203485385 hasConceptScore W3203485385C134306372 @default.
- W3203485385 hasConceptScore W3203485385C140331021 @default.
- W3203485385 hasConceptScore W3203485385C147037132 @default.
- W3203485385 hasConceptScore W3203485385C150899416 @default.
- W3203485385 hasConceptScore W3203485385C153180895 @default.
- W3203485385 hasConceptScore W3203485385C154945302 @default.
- W3203485385 hasConceptScore W3203485385C162324750 @default.
- W3203485385 hasConceptScore W3203485385C177264268 @default.
- W3203485385 hasConceptScore W3203485385C187736073 @default.
- W3203485385 hasConceptScore W3203485385C199360897 @default.