Matches in SemOpenAlex for { <https://semopenalex.org/work/W3089493605> ?p ?o ?g. }
- W3089493605 endingPage "182116" @default.
- W3089493605 startingPage "182105" @default.
- W3089493605 abstract "Domain adaptive object detection aims to build an object detector for the unlabeled target domain by transferring knowledge from a well-labeled source domain, which can alleviate the problem of cumbersome labeling of object detection in cross-scene power transmission line inspection. Remarkable advances are made recently by mitigating distributional shifts via hierarchical domain feature alignment training of detection networks. However, domain adaptive object detection is still limited in learning the invariance representation of multi-scale features. Specifically, the scale of objects varies in the scenes of aerial inspection, which hinders the knowledge transfer from the labeled source domain. In this paper, we propose a multi-scale feature enhanced domain adaptation method for cross-domain object detection of power transmission lines inspection. The proposed method consists of two components: 1) Multi-Scale Fusion Feature Alignment module (MSFA) to strengthen similar representation characteristics of different scales object in domain adaptive by utilizing context information conveyed from other levels; 2) Multi-Scale Consistency Regularization module (MSCR) to jointly optimize the multi-scale feature learning of each level, which promotes domain invariant feature learning at each level. Experimental results demonstrate that our method significantly increases the performance of the object detector in several cross-scene transmission line inspection tasks." @default.
- W3089493605 created "2020-10-08" @default.
- W3089493605 creator A5026828904 @default.
- W3089493605 creator A5053841398 @default.
- W3089493605 creator A5063517725 @default.
- W3089493605 creator A5065268407 @default.
- W3089493605 creator A5077558876 @default.
- W3089493605 creator A5081093007 @default.
- W3089493605 date "2020-01-01" @default.
- W3089493605 modified "2023-10-01" @default.
- W3089493605 title "Multi-Scale Feature Enhanced Domain Adaptive Object Detection For Power Transmission Line Inspection" @default.
- W3089493605 cites W1645888340 @default.
- W3089493605 cites W1832500336 @default.
- W3089493605 cites W1995063995 @default.
- W3089493605 cites W2004273576 @default.
- W3089493605 cites W2009671103 @default.
- W3089493605 cites W2031342017 @default.
- W3089493605 cites W2096943734 @default.
- W3089493605 cites W2102605133 @default.
- W3089493605 cites W2104094955 @default.
- W3089493605 cites W2108598243 @default.
- W3089493605 cites W2115403315 @default.
- W3089493605 cites W2128053425 @default.
- W3089493605 cites W2137528640 @default.
- W3089493605 cites W2161969291 @default.
- W3089493605 cites W2164598857 @default.
- W3089493605 cites W2165698076 @default.
- W3089493605 cites W2168356304 @default.
- W3089493605 cites W2341914330 @default.
- W3089493605 cites W2509784253 @default.
- W3089493605 cites W2517637548 @default.
- W3089493605 cites W2570343428 @default.
- W3089493605 cites W2593768305 @default.
- W3089493605 cites W2791049967 @default.
- W3089493605 cites W2798355657 @default.
- W3089493605 cites W2884771968 @default.
- W3089493605 cites W2889358773 @default.
- W3089493605 cites W2894878591 @default.
- W3089493605 cites W2895281799 @default.
- W3089493605 cites W2899812750 @default.
- W3089493605 cites W2904706552 @default.
- W3089493605 cites W2910009410 @default.
- W3089493605 cites W2943878449 @default.
- W3089493605 cites W2948069880 @default.
- W3089493605 cites W2955828465 @default.
- W3089493605 cites W2963037989 @default.
- W3089493605 cites W2963107255 @default.
- W3089493605 cites W2963150697 @default.
- W3089493605 cites W2963351448 @default.
- W3089493605 cites W2964115968 @default.
- W3089493605 cites W2964241181 @default.
- W3089493605 cites W2964288524 @default.
- W3089493605 cites W2965843558 @default.
- W3089493605 cites W2968634921 @default.
- W3089493605 cites W2969893028 @default.
- W3089493605 cites W2981512393 @default.
- W3089493605 cites W2982120826 @default.
- W3089493605 cites W2982770724 @default.
- W3089493605 cites W2990740643 @default.
- W3089493605 cites W2998216033 @default.
- W3089493605 cites W2998731096 @default.
- W3089493605 cites W3010456692 @default.
- W3089493605 cites W3015818151 @default.
- W3089493605 cites W3018638193 @default.
- W3089493605 cites W3021632667 @default.
- W3089493605 cites W3034779842 @default.
- W3089493605 cites W3035316790 @default.
- W3089493605 cites W639708223 @default.
- W3089493605 doi "https://doi.org/10.1109/access.2020.3027850" @default.
- W3089493605 hasPublicationYear "2020" @default.
- W3089493605 type Work @default.
- W3089493605 sameAs 3089493605 @default.
- W3089493605 citedByCount "7" @default.
- W3089493605 countsByYear W30894936052022 @default.
- W3089493605 countsByYear W30894936052023 @default.
- W3089493605 crossrefType "journal-article" @default.
- W3089493605 hasAuthorship W3089493605A5026828904 @default.
- W3089493605 hasAuthorship W3089493605A5053841398 @default.
- W3089493605 hasAuthorship W3089493605A5063517725 @default.
- W3089493605 hasAuthorship W3089493605A5065268407 @default.
- W3089493605 hasAuthorship W3089493605A5077558876 @default.
- W3089493605 hasAuthorship W3089493605A5081093007 @default.
- W3089493605 hasBestOaLocation W30894936051 @default.
- W3089493605 hasConcept C134306372 @default.
- W3089493605 hasConcept C138885662 @default.
- W3089493605 hasConcept C153180895 @default.
- W3089493605 hasConcept C154945302 @default.
- W3089493605 hasConcept C17744445 @default.
- W3089493605 hasConcept C199539241 @default.
- W3089493605 hasConcept C2776151529 @default.
- W3089493605 hasConcept C2776359362 @default.
- W3089493605 hasConcept C2776401178 @default.
- W3089493605 hasConcept C2776434776 @default.
- W3089493605 hasConcept C31972630 @default.
- W3089493605 hasConcept C33923547 @default.
- W3089493605 hasConcept C36503486 @default.
- W3089493605 hasConcept C41008148 @default.
- W3089493605 hasConcept C41895202 @default.