Matches in SemOpenAlex for { <https://semopenalex.org/work/W4382203405> ?p ?o ?g. }
- W4382203405 endingPage "15" @default.
- W4382203405 startingPage "1" @default.
- W4382203405 abstract "Object detection is essential in the interpretation of remote sensing images. However, the blurred background and objects with vast variances are identified as the two main challenges of the task. We propose a novel detector adapted to complicated background and multi-scale objects, namely, task-balanced multi-scale adaptive fusion network (TMAFNet), targeting directly on the above two challenges. Firstly, a depth separable global context module (DSGC) is constructed to understand contextual relations among pixels from a global perspective, which is extraordinarily necessary to distinguish objects from the environment. Most importantly, DSGC reduces the computational cost by decoupling the acquisition of global information into single-channel global interaction and multi-channel single-point interaction. Secondly, in order to eliminate disturbance and enhance representation ability of objects, hidden recursive feature pyramid network (HRFPN) is explored, which encodes the information of difference before and after using the multi-scale fusion. HRFPN is proven to enhance the target features by reducing the background noise. Thirdly, a semi-coupling task-balanced head (SCTB) is presented to guarantee the consistency of detection. We have conducted comprehensive experiments on several publicly available datasets, and the results illustrate that our modules improve adaptability and robustness of the network, leading to a new state-of-the-art." @default.
- W4382203405 created "2023-06-28" @default.
- W4382203405 creator A5012237055 @default.
- W4382203405 creator A5017578300 @default.
- W4382203405 creator A5017891986 @default.
- W4382203405 creator A5017947172 @default.
- W4382203405 creator A5061341525 @default.
- W4382203405 date "2023-01-01" @default.
- W4382203405 modified "2023-10-16" @default.
- W4382203405 title "A Task-Balanced Multi-Scale Adaptive Fusion Network for Object Detection in Remote Sensing Images" @default.
- W4382203405 cites W2102605133 @default.
- W4382203405 cites W2194775991 @default.
- W4382203405 cites W2512351403 @default.
- W4382203405 cites W2530966705 @default.
- W4382203405 cites W2565639579 @default.
- W4382203405 cites W2570343428 @default.
- W4382203405 cites W2577537809 @default.
- W4382203405 cites W2744389347 @default.
- W4382203405 cites W2747165560 @default.
- W4382203405 cites W2749439257 @default.
- W4382203405 cites W2904480641 @default.
- W4382203405 cites W2935079508 @default.
- W4382203405 cites W2963351448 @default.
- W4382203405 cites W2963857746 @default.
- W4382203405 cites W2964241181 @default.
- W4382203405 cites W2965522827 @default.
- W4382203405 cites W2966848223 @default.
- W4382203405 cites W2982770724 @default.
- W4382203405 cites W2989604896 @default.
- W4382203405 cites W2992240579 @default.
- W4382203405 cites W3009929949 @default.
- W4382203405 cites W3012573144 @default.
- W4382203405 cites W3034307881 @default.
- W4382203405 cites W3034552520 @default.
- W4382203405 cites W3034971973 @default.
- W4382203405 cites W3047443805 @default.
- W4382203405 cites W3048631361 @default.
- W4382203405 cites W3096609285 @default.
- W4382203405 cites W3103294617 @default.
- W4382203405 cites W3112264198 @default.
- W4382203405 cites W3113164744 @default.
- W4382203405 cites W3117374221 @default.
- W4382203405 cites W3136761610 @default.
- W4382203405 cites W3138516171 @default.
- W4382203405 cites W3138958001 @default.
- W4382203405 cites W3162930275 @default.
- W4382203405 cites W3175630421 @default.
- W4382203405 cites W3175894592 @default.
- W4382203405 cites W3176495987 @default.
- W4382203405 cites W3184840388 @default.
- W4382203405 cites W3193551430 @default.
- W4382203405 cites W3201260569 @default.
- W4382203405 cites W3208019692 @default.
- W4382203405 cites W3209073849 @default.
- W4382203405 cites W3209823299 @default.
- W4382203405 cites W4205932092 @default.
- W4382203405 cites W4206144626 @default.
- W4382203405 cites W4214507171 @default.
- W4382203405 cites W4226253382 @default.
- W4382203405 cites W4292387403 @default.
- W4382203405 cites W4308079983 @default.
- W4382203405 cites W4308237186 @default.
- W4382203405 cites W4312373555 @default.
- W4382203405 cites W4312653173 @default.
- W4382203405 cites W4313506322 @default.
- W4382203405 cites W4320713337 @default.
- W4382203405 cites W4366204749 @default.
- W4382203405 cites W639708223 @default.
- W4382203405 doi "https://doi.org/10.1109/tgrs.2023.3289878" @default.
- W4382203405 hasPublicationYear "2023" @default.
- W4382203405 type Work @default.
- W4382203405 citedByCount "0" @default.
- W4382203405 crossrefType "journal-article" @default.
- W4382203405 hasAuthorship W4382203405A5012237055 @default.
- W4382203405 hasAuthorship W4382203405A5017578300 @default.
- W4382203405 hasAuthorship W4382203405A5017891986 @default.
- W4382203405 hasAuthorship W4382203405A5017947172 @default.
- W4382203405 hasAuthorship W4382203405A5061341525 @default.
- W4382203405 hasConcept C104317684 @default.
- W4382203405 hasConcept C120665830 @default.
- W4382203405 hasConcept C121332964 @default.
- W4382203405 hasConcept C124101348 @default.
- W4382203405 hasConcept C142575187 @default.
- W4382203405 hasConcept C153180895 @default.
- W4382203405 hasConcept C154945302 @default.
- W4382203405 hasConcept C160633673 @default.
- W4382203405 hasConcept C177606310 @default.
- W4382203405 hasConcept C185592680 @default.
- W4382203405 hasConcept C18903297 @default.
- W4382203405 hasConcept C2776151529 @default.
- W4382203405 hasConcept C31972630 @default.
- W4382203405 hasConcept C33954974 @default.
- W4382203405 hasConcept C41008148 @default.
- W4382203405 hasConcept C55493867 @default.
- W4382203405 hasConcept C63479239 @default.
- W4382203405 hasConcept C86803240 @default.
- W4382203405 hasConceptScore W4382203405C104317684 @default.
- W4382203405 hasConceptScore W4382203405C120665830 @default.