Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285179511> ?p ?o ?g. }
- W4285179511 endingPage "16" @default.
- W4285179511 startingPage "1" @default.
- W4285179511 abstract "Object detection in aerial images, different from general object detection, faces with several challenges such as arbitrary-oriented objects and extremely imbalanced foreground-background distribution. Although some recent proposed aerial object detection methods achieve promising results, they are mainly anchor-based detectors which rely heavily on pre-defined anchor boxes and the final detection performance is sensitive to anchor-related hyper-parameters. In contrast, in this paper, we present an anchor-free detector with feature enhancement and soft label assignment (FSDet) which adopts a simpler design and achieves competitive performance. Specifically, to address the feature misalignment for detecting oriented objects, we propose an oriented feature refinement module to align the features with oriented objects. To alleviate the background issue, we design a class-aware context aggregation module to integrate the intra-class context information and suppress background context. Moreover, we propose a soft label assignment mechanism to measure the weight of training samples within the arbitrary-oriented objects, which can concentrate more on representative items with regard to their potential to detect oriented objects, achieving a more stable optimization during training. Extensive experiments on several datasets suggest that the proposed method is superior to the state-of-the-art methods and achieves a better trade-off between speed and accuracy." @default.
- W4285179511 created "2022-07-14" @default.
- W4285179511 creator A5011324535 @default.
- W4285179511 creator A5062655544 @default.
- W4285179511 creator A5068252474 @default.
- W4285179511 creator A5078167954 @default.
- W4285179511 date "2022-01-01" @default.
- W4285179511 modified "2023-10-13" @default.
- W4285179511 title "Object Detection for Aerial Images With Feature Enhancement and Soft Label Assignment" @default.
- W4285179511 cites W1536680647 @default.
- W4285179511 cites W2102605133 @default.
- W4285179511 cites W2194775991 @default.
- W4285179511 cites W2296151615 @default.
- W4285179511 cites W2565639579 @default.
- W4285179511 cites W2601564443 @default.
- W4285179511 cites W2788202095 @default.
- W4285179511 cites W2888527098 @default.
- W4285179511 cites W2899594603 @default.
- W4285179511 cites W2962749812 @default.
- W4285179511 cites W2962766617 @default.
- W4285179511 cites W2963150697 @default.
- W4285179511 cites W2963351448 @default.
- W4285179511 cites W2963849369 @default.
- W4285179511 cites W2964294787 @default.
- W4285179511 cites W2964979676 @default.
- W4285179511 cites W2982770724 @default.
- W4285179511 cites W2991359031 @default.
- W4285179511 cites W2991363140 @default.
- W4285179511 cites W3010864078 @default.
- W4285179511 cites W3034993937 @default.
- W4285179511 cites W3035396860 @default.
- W4285179511 cites W3048939508 @default.
- W4285179511 cites W3097779785 @default.
- W4285179511 cites W3098218837 @default.
- W4285179511 cites W3102701618 @default.
- W4285179511 cites W3106228955 @default.
- W4285179511 cites W3108849448 @default.
- W4285179511 cites W3109055651 @default.
- W4285179511 cites W3119027652 @default.
- W4285179511 cites W3120031785 @default.
- W4285179511 cites W3170033848 @default.
- W4285179511 cites W4211247672 @default.
- W4285179511 cites W4214648418 @default.
- W4285179511 doi "https://doi.org/10.1109/tgrs.2022.3177255" @default.
- W4285179511 hasPublicationYear "2022" @default.
- W4285179511 type Work @default.
- W4285179511 citedByCount "6" @default.
- W4285179511 countsByYear W42851795112023 @default.
- W4285179511 crossrefType "journal-article" @default.
- W4285179511 hasAuthorship W4285179511A5011324535 @default.
- W4285179511 hasAuthorship W4285179511A5062655544 @default.
- W4285179511 hasAuthorship W4285179511A5068252474 @default.
- W4285179511 hasAuthorship W4285179511A5078167954 @default.
- W4285179511 hasConcept C138885662 @default.
- W4285179511 hasConcept C151730666 @default.
- W4285179511 hasConcept C153180895 @default.
- W4285179511 hasConcept C154945302 @default.
- W4285179511 hasConcept C2776151529 @default.
- W4285179511 hasConcept C2776401178 @default.
- W4285179511 hasConcept C2777212361 @default.
- W4285179511 hasConcept C2779343474 @default.
- W4285179511 hasConcept C2781238097 @default.
- W4285179511 hasConcept C31972630 @default.
- W4285179511 hasConcept C41008148 @default.
- W4285179511 hasConcept C41895202 @default.
- W4285179511 hasConcept C52622490 @default.
- W4285179511 hasConcept C76155785 @default.
- W4285179511 hasConcept C86803240 @default.
- W4285179511 hasConcept C94915269 @default.
- W4285179511 hasConceptScore W4285179511C138885662 @default.
- W4285179511 hasConceptScore W4285179511C151730666 @default.
- W4285179511 hasConceptScore W4285179511C153180895 @default.
- W4285179511 hasConceptScore W4285179511C154945302 @default.
- W4285179511 hasConceptScore W4285179511C2776151529 @default.
- W4285179511 hasConceptScore W4285179511C2776401178 @default.
- W4285179511 hasConceptScore W4285179511C2777212361 @default.
- W4285179511 hasConceptScore W4285179511C2779343474 @default.
- W4285179511 hasConceptScore W4285179511C2781238097 @default.
- W4285179511 hasConceptScore W4285179511C31972630 @default.
- W4285179511 hasConceptScore W4285179511C41008148 @default.
- W4285179511 hasConceptScore W4285179511C41895202 @default.
- W4285179511 hasConceptScore W4285179511C52622490 @default.
- W4285179511 hasConceptScore W4285179511C76155785 @default.
- W4285179511 hasConceptScore W4285179511C86803240 @default.
- W4285179511 hasConceptScore W4285179511C94915269 @default.
- W4285179511 hasFunder F4320321001 @default.
- W4285179511 hasLocation W42851795111 @default.
- W4285179511 hasOpenAccess W4285179511 @default.
- W4285179511 hasPrimaryLocation W42851795111 @default.
- W4285179511 hasRelatedWork W1837097281 @default.
- W4285179511 hasRelatedWork W1966410754 @default.
- W4285179511 hasRelatedWork W1988485990 @default.
- W4285179511 hasRelatedWork W2007544051 @default.
- W4285179511 hasRelatedWork W2095705906 @default.
- W4285179511 hasRelatedWork W2334336442 @default.
- W4285179511 hasRelatedWork W2546942002 @default.
- W4285179511 hasRelatedWork W2732308154 @default.
- W4285179511 hasRelatedWork W2975200075 @default.