Matches in SemOpenAlex for { <https://semopenalex.org/work/W3090765900> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W3090765900 abstract "Manually generating annotated bounding boxes for object detection is time consuming. Although human-annotation is the most accurate approach, machine learning models can provide additional assistance. In this paper, we propose a human in a loop automatic image labeling framework focusing on aerial images with less features for detection. The proposed model consists of two main parts, prediction model and adjustment model. The user first provides click location to prediction model to generate a bounding box of a specific object. The bounding box is then fine-tuned by the adjustment model for more accurate size and location. A feedback and retrain mechanism is implemented that allows the users to manually adjust the generated bounding box and provide feedback to incrementally train the adjustment network during runtime. This unique online learning feature enables user to generalize existing model to target classes not initially presented in the training set, and gradually improves the specificity of the model to those new targets online. We demonstrate promising results on Neovision 2 Heli dataset. Compared to the state-of-the-art method, our prediction model achieves a higher detection rate, and our adjustment model improves the IOU by up to 45%" @default.
- W3090765900 created "2020-10-08" @default.
- W3090765900 creator A5018468480 @default.
- W3090765900 creator A5080248485 @default.
- W3090765900 creator A5083642251 @default.
- W3090765900 creator A5088334760 @default.
- W3090765900 date "2020-07-01" @default.
- W3090765900 modified "2023-09-24" @default.
- W3090765900 title "Automatic Image Labeling with Click Supervision on Aerial Images" @default.
- W3090765900 cites W1849277567 @default.
- W3090765900 cites W1861492603 @default.
- W3090765900 cites W1953465585 @default.
- W3090765900 cites W2031489346 @default.
- W3090765900 cites W2117539524 @default.
- W3090765900 cites W2133324800 @default.
- W3090765900 cites W2147800946 @default.
- W3090765900 cites W2152411181 @default.
- W3090765900 cites W2163605009 @default.
- W3090765900 cites W2169374938 @default.
- W3090765900 cites W2565639579 @default.
- W3090765900 cites W2608567823 @default.
- W3090765900 cites W2613718673 @default.
- W3090765900 cites W2776163999 @default.
- W3090765900 cites W2795068684 @default.
- W3090765900 cites W2796347433 @default.
- W3090765900 cites W2963037989 @default.
- W3090765900 cites W2964073328 @default.
- W3090765900 cites W3106250896 @default.
- W3090765900 cites W611457968 @default.
- W3090765900 doi "https://doi.org/10.1109/ijcnn48605.2020.9207363" @default.
- W3090765900 hasPublicationYear "2020" @default.
- W3090765900 type Work @default.
- W3090765900 sameAs 3090765900 @default.
- W3090765900 citedByCount "1" @default.
- W3090765900 countsByYear W30907659002021 @default.
- W3090765900 crossrefType "proceedings-article" @default.
- W3090765900 hasAuthorship W3090765900A5018468480 @default.
- W3090765900 hasAuthorship W3090765900A5080248485 @default.
- W3090765900 hasAuthorship W3090765900A5083642251 @default.
- W3090765900 hasAuthorship W3090765900A5088334760 @default.
- W3090765900 hasConcept C115961682 @default.
- W3090765900 hasConcept C119857082 @default.
- W3090765900 hasConcept C124101348 @default.
- W3090765900 hasConcept C138885662 @default.
- W3090765900 hasConcept C147037132 @default.
- W3090765900 hasConcept C153180895 @default.
- W3090765900 hasConcept C154945302 @default.
- W3090765900 hasConcept C177264268 @default.
- W3090765900 hasConcept C199360897 @default.
- W3090765900 hasConcept C2776151529 @default.
- W3090765900 hasConcept C2776321320 @default.
- W3090765900 hasConcept C2776401178 @default.
- W3090765900 hasConcept C2781238097 @default.
- W3090765900 hasConcept C31972630 @default.
- W3090765900 hasConcept C41008148 @default.
- W3090765900 hasConcept C41895202 @default.
- W3090765900 hasConcept C52622490 @default.
- W3090765900 hasConcept C63584917 @default.
- W3090765900 hasConceptScore W3090765900C115961682 @default.
- W3090765900 hasConceptScore W3090765900C119857082 @default.
- W3090765900 hasConceptScore W3090765900C124101348 @default.
- W3090765900 hasConceptScore W3090765900C138885662 @default.
- W3090765900 hasConceptScore W3090765900C147037132 @default.
- W3090765900 hasConceptScore W3090765900C153180895 @default.
- W3090765900 hasConceptScore W3090765900C154945302 @default.
- W3090765900 hasConceptScore W3090765900C177264268 @default.
- W3090765900 hasConceptScore W3090765900C199360897 @default.
- W3090765900 hasConceptScore W3090765900C2776151529 @default.
- W3090765900 hasConceptScore W3090765900C2776321320 @default.
- W3090765900 hasConceptScore W3090765900C2776401178 @default.
- W3090765900 hasConceptScore W3090765900C2781238097 @default.
- W3090765900 hasConceptScore W3090765900C31972630 @default.
- W3090765900 hasConceptScore W3090765900C41008148 @default.
- W3090765900 hasConceptScore W3090765900C41895202 @default.
- W3090765900 hasConceptScore W3090765900C52622490 @default.
- W3090765900 hasConceptScore W3090765900C63584917 @default.
- W3090765900 hasLocation W30907659001 @default.
- W3090765900 hasOpenAccess W3090765900 @default.
- W3090765900 hasPrimaryLocation W30907659001 @default.
- W3090765900 hasRelatedWork W1000462 @default.
- W3090765900 hasRelatedWork W1284803 @default.
- W3090765900 hasRelatedWork W2803426 @default.
- W3090765900 hasRelatedWork W4486015 @default.
- W3090765900 hasRelatedWork W7237889 @default.
- W3090765900 hasRelatedWork W724576 @default.
- W3090765900 hasRelatedWork W7746136 @default.
- W3090765900 hasRelatedWork W9122165 @default.
- W3090765900 hasRelatedWork W9402503 @default.
- W3090765900 hasRelatedWork W11907932 @default.
- W3090765900 isParatext "false" @default.
- W3090765900 isRetracted "false" @default.
- W3090765900 magId "3090765900" @default.
- W3090765900 workType "article" @default.