Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386869748> ?p ?o ?g. }
- W4386869748 endingPage "11" @default.
- W4386869748 startingPage "1" @default.
- W4386869748 abstract "Remote sensing object labels require high specialization, resulting in a limited number of labeled samples. Without large labeled samples to support training, general remote sensing object recognition models have limited accuracy. Addressing this issue, this paper proposes a weakly correlated distillation learning framework for remote sensing object recognition with small number of samples. Benefitting from large-scale natural image datasets, many recognition models achieve superior feature extraction capabilities. Thus, we use them as backbones to build teacher models, and then fine-tune the teacher models with a small-scale remote sensing dataset. However, due to the limited number of remote sensing samples, the teacher models may produce noisy features that reduce the performance of the student model. Therefore, we propose a weakly correlated distillation method that selects the weakly correlated features from teacher models to distill the student. Since the weakly correlated features contain different noise distributions which can be mutually suppressed, thereby improving the performance of the student. Extensive experiments on three widely-used datasets of DOTA, HRRSD and NWPU VHR-10 demonstrate the superior performance of our method compared with the state of the arts. Code is available at: https://github.com/wdzhao123/WCD." @default.
- W4386869748 created "2023-09-20" @default.
- W4386869748 creator A5005082707 @default.
- W4386869748 creator A5006986293 @default.
- W4386869748 creator A5010642607 @default.
- W4386869748 creator A5014876180 @default.
- W4386869748 creator A5045263999 @default.
- W4386869748 creator A5090447493 @default.
- W4386869748 date "2023-01-01" @default.
- W4386869748 modified "2023-10-15" @default.
- W4386869748 title "Weakly Correlated Distillation for Remote Sensing Object Recognition" @default.
- W4386869748 cites W2108598243 @default.
- W4386869748 cites W2163345210 @default.
- W4386869748 cites W2194775991 @default.
- W4386869748 cites W2512351403 @default.
- W4386869748 cites W2747909401 @default.
- W4386869748 cites W2885722830 @default.
- W4386869748 cites W2935079508 @default.
- W4386869748 cites W2948582784 @default.
- W4386869748 cites W2949736877 @default.
- W4386869748 cites W2962749812 @default.
- W4386869748 cites W2963070905 @default.
- W4386869748 cites W2963446712 @default.
- W4386869748 cites W2987861506 @default.
- W4386869748 cites W2997006708 @default.
- W4386869748 cites W2997073599 @default.
- W4386869748 cites W2997351135 @default.
- W4386869748 cites W2998823187 @default.
- W4386869748 cites W3035163969 @default.
- W4386869748 cites W3037215700 @default.
- W4386869748 cites W3040987333 @default.
- W4386869748 cites W3046698617 @default.
- W4386869748 cites W3091762728 @default.
- W4386869748 cites W3096121526 @default.
- W4386869748 cites W3108549452 @default.
- W4386869748 cites W3108870912 @default.
- W4386869748 cites W3119762784 @default.
- W4386869748 cites W3128731563 @default.
- W4386869748 cites W3129242818 @default.
- W4386869748 cites W3129617769 @default.
- W4386869748 cites W3159493336 @default.
- W4386869748 cites W3173547984 @default.
- W4386869748 cites W3173788280 @default.
- W4386869748 cites W3175215201 @default.
- W4386869748 cites W3177450132 @default.
- W4386869748 cites W3197671932 @default.
- W4386869748 cites W4213218297 @default.
- W4386869748 cites W4220816550 @default.
- W4386869748 cites W4226291728 @default.
- W4386869748 cites W4285123352 @default.
- W4386869748 cites W4312235460 @default.
- W4386869748 cites W4312359569 @default.
- W4386869748 cites W4312500832 @default.
- W4386869748 cites W4312551518 @default.
- W4386869748 cites W4312626422 @default.
- W4386869748 cites W4312762894 @default.
- W4386869748 cites W4312830051 @default.
- W4386869748 cites W4312875660 @default.
- W4386869748 cites W4312938578 @default.
- W4386869748 cites W4313049560 @default.
- W4386869748 cites W4313066313 @default.
- W4386869748 cites W4313160267 @default.
- W4386869748 cites W4382240034 @default.
- W4386869748 doi "https://doi.org/10.1109/tgrs.2023.3317264" @default.
- W4386869748 hasPublicationYear "2023" @default.
- W4386869748 type Work @default.
- W4386869748 citedByCount "0" @default.
- W4386869748 crossrefType "journal-article" @default.
- W4386869748 hasAuthorship W4386869748A5005082707 @default.
- W4386869748 hasAuthorship W4386869748A5006986293 @default.
- W4386869748 hasAuthorship W4386869748A5010642607 @default.
- W4386869748 hasAuthorship W4386869748A5014876180 @default.
- W4386869748 hasAuthorship W4386869748A5045263999 @default.
- W4386869748 hasAuthorship W4386869748A5090447493 @default.
- W4386869748 hasConcept C115961682 @default.
- W4386869748 hasConcept C119857082 @default.
- W4386869748 hasConcept C121332964 @default.
- W4386869748 hasConcept C124101348 @default.
- W4386869748 hasConcept C127313418 @default.
- W4386869748 hasConcept C138885662 @default.
- W4386869748 hasConcept C153180895 @default.
- W4386869748 hasConcept C154945302 @default.
- W4386869748 hasConcept C177264268 @default.
- W4386869748 hasConcept C178790620 @default.
- W4386869748 hasConcept C185592680 @default.
- W4386869748 hasConcept C199360897 @default.
- W4386869748 hasConcept C204030448 @default.
- W4386869748 hasConcept C2776151529 @default.
- W4386869748 hasConcept C2776401178 @default.
- W4386869748 hasConcept C2776760102 @default.
- W4386869748 hasConcept C2778755073 @default.
- W4386869748 hasConcept C2781238097 @default.
- W4386869748 hasConcept C41008148 @default.
- W4386869748 hasConcept C41895202 @default.
- W4386869748 hasConcept C52622490 @default.
- W4386869748 hasConcept C62520636 @default.
- W4386869748 hasConcept C62649853 @default.
- W4386869748 hasConcept C64876066 @default.