Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384080779> ?p ?o ?g. }
- W4384080779 endingPage "15" @default.
- W4384080779 startingPage "1" @default.
- W4384080779 abstract "The aerial objects tend to distribute with a major variation on the scale and arbitrary orientations in remote sensing images. To meet such characteristics of the aerial object, most of the existing anchor-based detectors rely on preset anchors with variable scales, angles, and aspect ratios, which leads to the misalignment of the selection of candidate regions, the extraction of object features, and the label assignment of preset boxes, interfering the performance of the detector. To address this issue, we propose a Hierarchical Adaptive Alignment Network (HAA-Net). Specifically, we first design the Region Refinement Module (RRM), Feature Alignment module (FAM), and Potential Label Assignment Module (PLAM) to alleviate the misalignment of the region, feature, and label levels respectively; furthermore, we use the gradient equalization strategy to jointly optimize these modules at different levels, so that the whole network can be fully trained to significantly improve detection performance. Extensive experiments demonstrate that our approach can achieve superior performance in three common aerial object datasets (e.g., DOTA, HRSC2016, and UCAS-AOD) when compared with state-of-the-art detectors." @default.
- W4384080779 created "2023-07-13" @default.
- W4384080779 creator A5024498727 @default.
- W4384080779 creator A5035508615 @default.
- W4384080779 creator A5044435891 @default.
- W4384080779 creator A5079668307 @default.
- W4384080779 date "2023-01-01" @default.
- W4384080779 modified "2023-10-11" @default.
- W4384080779 title "Toward Hierarchical Adaptive Alignment for Aerial Object Detection in Remote Sensing Images" @default.
- W4384080779 cites W2061200049 @default.
- W4384080779 cites W2100503224 @default.
- W4384080779 cites W2296151615 @default.
- W4384080779 cites W2412558220 @default.
- W4384080779 cites W2594177559 @default.
- W4384080779 cites W2596246567 @default.
- W4384080779 cites W2597117158 @default.
- W4384080779 cites W2601564443 @default.
- W4384080779 cites W2790688320 @default.
- W4384080779 cites W2792075695 @default.
- W4384080779 cites W2796164853 @default.
- W4384080779 cites W2800388963 @default.
- W4384080779 cites W2802773275 @default.
- W4384080779 cites W2884561390 @default.
- W4384080779 cites W2899594603 @default.
- W4384080779 cites W2953867371 @default.
- W4384080779 cites W2962721361 @default.
- W4384080779 cites W2962749812 @default.
- W4384080779 cites W2963037989 @default.
- W4384080779 cites W2963113370 @default.
- W4384080779 cites W2963179609 @default.
- W4384080779 cites W2963516811 @default.
- W4384080779 cites W2964241181 @default.
- W4384080779 cites W2964294787 @default.
- W4384080779 cites W2964979676 @default.
- W4384080779 cites W2991359031 @default.
- W4384080779 cites W2991363140 @default.
- W4384080779 cites W2993501994 @default.
- W4384080779 cites W3004492228 @default.
- W4384080779 cites W3015331846 @default.
- W4384080779 cites W3022917557 @default.
- W4384080779 cites W3035524459 @default.
- W4384080779 cites W3046174881 @default.
- W4384080779 cites W3080104546 @default.
- W4384080779 cites W3080577187 @default.
- W4384080779 cites W3098218837 @default.
- W4384080779 cites W3106228955 @default.
- W4384080779 cites W3107867277 @default.
- W4384080779 cites W3108849448 @default.
- W4384080779 cites W3119027652 @default.
- W4384080779 cites W3121842289 @default.
- W4384080779 cites W3134025014 @default.
- W4384080779 cites W3136761610 @default.
- W4384080779 cites W3141404903 @default.
- W4384080779 cites W3144293580 @default.
- W4384080779 cites W3167308647 @default.
- W4384080779 cites W3172087149 @default.
- W4384080779 cites W3174389852 @default.
- W4384080779 cites W3174873843 @default.
- W4384080779 cites W3182848941 @default.
- W4384080779 cites W3214821343 @default.
- W4384080779 cites W4211247672 @default.
- W4384080779 cites W4229032258 @default.
- W4384080779 cites W4285109597 @default.
- W4384080779 cites W4285295475 @default.
- W4384080779 cites W4293075084 @default.
- W4384080779 cites W4308173664 @default.
- W4384080779 cites W639708223 @default.
- W4384080779 doi "https://doi.org/10.1109/tgrs.2023.3294520" @default.
- W4384080779 hasPublicationYear "2023" @default.
- W4384080779 type Work @default.
- W4384080779 citedByCount "1" @default.
- W4384080779 crossrefType "journal-article" @default.
- W4384080779 hasAuthorship W4384080779A5024498727 @default.
- W4384080779 hasAuthorship W4384080779A5035508615 @default.
- W4384080779 hasAuthorship W4384080779A5044435891 @default.
- W4384080779 hasAuthorship W4384080779A5079668307 @default.
- W4384080779 hasConcept C115961682 @default.
- W4384080779 hasConcept C121332964 @default.
- W4384080779 hasConcept C127313418 @default.
- W4384080779 hasConcept C138885662 @default.
- W4384080779 hasConcept C153180895 @default.
- W4384080779 hasConcept C154945302 @default.
- W4384080779 hasConcept C2776151529 @default.
- W4384080779 hasConcept C2776401178 @default.
- W4384080779 hasConcept C2776429412 @default.
- W4384080779 hasConcept C2778755073 @default.
- W4384080779 hasConcept C2781238097 @default.
- W4384080779 hasConcept C31972630 @default.
- W4384080779 hasConcept C41008148 @default.
- W4384080779 hasConcept C41895202 @default.
- W4384080779 hasConcept C52622490 @default.
- W4384080779 hasConcept C62520636 @default.
- W4384080779 hasConcept C62649853 @default.
- W4384080779 hasConcept C76155785 @default.
- W4384080779 hasConcept C94915269 @default.
- W4384080779 hasConceptScore W4384080779C115961682 @default.
- W4384080779 hasConceptScore W4384080779C121332964 @default.
- W4384080779 hasConceptScore W4384080779C127313418 @default.