Matches in SemOpenAlex for { <https://semopenalex.org/work/W3174443671> ?p ?o ?g. }
- W3174443671 abstract "In deep learning-based object detection on remote sensing domain, nuisance factors, which affect observed variables while not affecting predictor variables, often matters because they cause domain changes. Previously, nuisance disentangled feature transformation (NDFT) was proposed to build domain-invariant feature extractor with with knowledge of nuisance factors. However, NDFT requires enormous time in a training phase, so it has been impractical. In this paper, we introduce our proposed method, A-NDFT, which is an improvement to NDFT. A-NDFT utilizes two acceleration techniques, feature replay and slow learner. Consequently, on a large-scale UAVDT benchmark, it is shown that our framework can reduce the training time of NDFT from 31 hours to 3 hours while still maintaining the performance. The code will be made publicly available online <sup xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>1</sup> ." @default.
- W3174443671 created "2021-07-05" @default.
- W3174443671 creator A5000629292 @default.
- W3174443671 creator A5064276223 @default.
- W3174443671 creator A5085035593 @default.
- W3174443671 date "2021-06-01" @default.
- W3174443671 modified "2023-10-02" @default.
- W3174443671 title "Training Domain-invariant Object Detector Faster with Feature Replay and Slow Learner" @default.
- W3174443671 cites W1828453565 @default.
- W3174443671 cites W2116522068 @default.
- W3174443671 cites W2145339207 @default.
- W3174443671 cites W2151750630 @default.
- W3174443671 cites W2798813225 @default.
- W3174443671 cites W2883820570 @default.
- W3174443671 cites W2884985453 @default.
- W3174443671 cites W2891975605 @default.
- W3174443671 cites W2917187459 @default.
- W3174443671 cites W2929499422 @default.
- W3174443671 cites W2935837427 @default.
- W3174443671 cites W2938671123 @default.
- W3174443671 cites W2962777203 @default.
- W3174443671 cites W2963229629 @default.
- W3174443671 cites W2963271314 @default.
- W3174443671 cites W2963446520 @default.
- W3174443671 cites W2963709863 @default.
- W3174443671 cites W2963783084 @default.
- W3174443671 cites W2963785576 @default.
- W3174443671 cites W2963826681 @default.
- W3174443671 cites W2970586779 @default.
- W3174443671 cites W2972395464 @default.
- W3174443671 cites W2981705647 @default.
- W3174443671 cites W2982164728 @default.
- W3174443671 cites W2985374865 @default.
- W3174443671 cites W2998503299 @default.
- W3174443671 cites W2998802733 @default.
- W3174443671 cites W3005568369 @default.
- W3174443671 cites W3013664265 @default.
- W3174443671 cites W3025070692 @default.
- W3174443671 cites W3034285949 @default.
- W3174443671 cites W3034814687 @default.
- W3174443671 cites W3034858314 @default.
- W3174443671 cites W3034937575 @default.
- W3174443671 cites W3035060554 @default.
- W3174443671 cites W3035804495 @default.
- W3174443671 cites W3106250896 @default.
- W3174443671 cites W3115919227 @default.
- W3174443671 cites W3128088035 @default.
- W3174443671 cites W3148140980 @default.
- W3174443671 cites W639708223 @default.
- W3174443671 doi "https://doi.org/10.1109/cvprw53098.2021.00128" @default.
- W3174443671 hasPublicationYear "2021" @default.
- W3174443671 type Work @default.
- W3174443671 sameAs 3174443671 @default.
- W3174443671 citedByCount "1" @default.
- W3174443671 countsByYear W31744436712023 @default.
- W3174443671 crossrefType "proceedings-article" @default.
- W3174443671 hasAuthorship W3174443671A5000629292 @default.
- W3174443671 hasAuthorship W3174443671A5064276223 @default.
- W3174443671 hasAuthorship W3174443671A5085035593 @default.
- W3174443671 hasBestOaLocation W31744436712 @default.
- W3174443671 hasConcept C117978034 @default.
- W3174443671 hasConcept C127413603 @default.
- W3174443671 hasConcept C13280743 @default.
- W3174443671 hasConcept C134306372 @default.
- W3174443671 hasConcept C138885662 @default.
- W3174443671 hasConcept C153180895 @default.
- W3174443671 hasConcept C154945302 @default.
- W3174443671 hasConcept C185798385 @default.
- W3174443671 hasConcept C190470478 @default.
- W3174443671 hasConcept C205649164 @default.
- W3174443671 hasConcept C21880701 @default.
- W3174443671 hasConcept C2776151529 @default.
- W3174443671 hasConcept C2776401178 @default.
- W3174443671 hasConcept C33923547 @default.
- W3174443671 hasConcept C36503486 @default.
- W3174443671 hasConcept C37914503 @default.
- W3174443671 hasConcept C41008148 @default.
- W3174443671 hasConcept C41895202 @default.
- W3174443671 hasConcept C52622490 @default.
- W3174443671 hasConcept C76155785 @default.
- W3174443671 hasConcept C94915269 @default.
- W3174443671 hasConceptScore W3174443671C117978034 @default.
- W3174443671 hasConceptScore W3174443671C127413603 @default.
- W3174443671 hasConceptScore W3174443671C13280743 @default.
- W3174443671 hasConceptScore W3174443671C134306372 @default.
- W3174443671 hasConceptScore W3174443671C138885662 @default.
- W3174443671 hasConceptScore W3174443671C153180895 @default.
- W3174443671 hasConceptScore W3174443671C154945302 @default.
- W3174443671 hasConceptScore W3174443671C185798385 @default.
- W3174443671 hasConceptScore W3174443671C190470478 @default.
- W3174443671 hasConceptScore W3174443671C205649164 @default.
- W3174443671 hasConceptScore W3174443671C21880701 @default.
- W3174443671 hasConceptScore W3174443671C2776151529 @default.
- W3174443671 hasConceptScore W3174443671C2776401178 @default.
- W3174443671 hasConceptScore W3174443671C33923547 @default.
- W3174443671 hasConceptScore W3174443671C36503486 @default.
- W3174443671 hasConceptScore W3174443671C37914503 @default.
- W3174443671 hasConceptScore W3174443671C41008148 @default.
- W3174443671 hasConceptScore W3174443671C41895202 @default.
- W3174443671 hasConceptScore W3174443671C52622490 @default.