FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312479381> ?p ?o ?g. }

• W4312479381 endingPage "14" @default.
• W4312479381 startingPage "1" @default.
• W4312479381 abstract "In the area of optical remote sensing image processing, object detection is among the utmost essential and difficult tasks. By virtue of the excellent feature representation abilities of deep convolutional neural networks (DCNNs), the performance of remote sensing object detection has recently increased dramatically. However, DCNN-based methods necessitate sufficient labeled training samples and tend to experience a considerable performance fall when training examples are insufficient. Many of the recently developed few-shot object detection (FSOD) methods attempt to solve the issue by using the idea of meta-learning, which intends to extract knowledge that can be generalized across various tasks. Despite its success, the negligence of the knowledge learned in the past, and inter-class correlations hinder the detection ability of novel classes. In this article, we propose a new meta-memory based FSOD approach named MM-RCNN. Specifically, MM-RCNN adopts a memory moduel to store each category’s knowledge learned in the training stage and the memory-based external attention (MEA) to aggregate all categories’ information simultaneously. Based on MEA, we design two feature enhancement modules for the region proposal network (RPN) and detection head to boost the performance. Experiments over two remote sensing benchmarks, i.e., DIOR and NWPU VHR10, verify the capability of our method (0.239 and 0.557 average mAP across all settings)." @default.
• W4312479381 created "2023-01-05" @default.
• W4312479381 creator A5004269762 @default.
• W4312479381 creator A5009491692 @default.
• W4312479381 creator A5011426350 @default.
• W4312479381 creator A5014742984 @default.
• W4312479381 creator A5043420125 @default.
• W4312479381 creator A5052220949 @default.
• W4312479381 creator A5077251537 @default.
• W4312479381 date "2022-01-01" @default.
• W4312479381 modified "2023-09-28" @default.
• W4312479381 title "MM-RCNN: Toward Few-Shot Object Detection in Remote Sensing Images With Meta Memory" @default.
• W4312479381 cites W2003059629 @default.
• W4312479381 cites W2005368619 @default.
• W4312479381 cites W2031489346 @default.
• W4312479381 cites W2108598243 @default.
• W4312479381 cites W2194775991 @default.
• W4312479381 cites W2308318555 @default.
• W4312479381 cites W2341088578 @default.
• W4312479381 cites W2343118941 @default.
• W4312479381 cites W2412588858 @default.
• W4312479381 cites W2570343428 @default.
• W4312479381 cites W2601564443 @default.
• W4312479381 cites W2779335303 @default.
• W4312479381 cites W2782522152 @default.
• W4312479381 cites W2800388963 @default.
• W4312479381 cites W2803867573 @default.
• W4312479381 cites W2884585870 @default.
• W4312479381 cites W2888527098 @default.
• W4312479381 cites W2962837320 @default.
• W4312479381 cites W2963037989 @default.
• W4312479381 cites W2963091558 @default.
• W4312479381 cites W2963150697 @default.
• W4312479381 cites W2963351448 @default.
• W4312479381 cites W2963420686 @default.
• W4312479381 cites W2963927307 @default.
• W4312479381 cites W2967073193 @default.
• W4312479381 cites W2981689412 @default.
• W4312479381 cites W2983156430 @default.
• W4312479381 cites W2991363140 @default.
• W4312479381 cites W2992240579 @default.
• W4312479381 cites W2996583130 @default.
• W4312479381 cites W3004492228 @default.
• W4312479381 cites W3041014620 @default.
• W4312479381 cites W3047443805 @default.
• W4312479381 cites W3048091868 @default.
• W4312479381 cites W3048631361 @default.
• W4312479381 cites W3103294617 @default.
• W4312479381 cites W3125372245 @default.
• W4312479381 cites W3132437036 @default.
• W4312479381 cites W3134025014 @default.
• W4312479381 cites W3144293580 @default.
• W4312479381 cites W3169708801 @default.
• W4312479381 cites W3174396556 @default.
• W4312479381 cites W3175577495 @default.
• W4312479381 cites W3190905519 @default.
• W4312479381 cites W3191799143 @default.
• W4312479381 cites W3203229600 @default.
• W4312479381 cites W3205363943 @default.
• W4312479381 cites W3209540366 @default.
• W4312479381 cites W4211247672 @default.
• W4312479381 cites W4302275239 @default.
• W4312479381 cites W4313123084 @default.
• W4312479381 doi "https://doi.org/10.1109/tgrs.2022.3228612" @default.
• W4312479381 hasPublicationYear "2022" @default.
• W4312479381 type Work @default.
• W4312479381 citedByCount "6" @default.
• W4312479381 countsByYear W43124793812022 @default.
• W4312479381 countsByYear W43124793812023 @default.
• W4312479381 crossrefType "journal-article" @default.
• W4312479381 hasAuthorship W4312479381A5004269762 @default.
• W4312479381 hasAuthorship W4312479381A5009491692 @default.
• W4312479381 hasAuthorship W4312479381A5011426350 @default.
• W4312479381 hasAuthorship W4312479381A5014742984 @default.
• W4312479381 hasAuthorship W4312479381A5043420125 @default.
• W4312479381 hasAuthorship W4312479381A5052220949 @default.
• W4312479381 hasAuthorship W4312479381A5077251537 @default.
• W4312479381 hasConcept C138885662 @default.
• W4312479381 hasConcept C153180895 @default.
• W4312479381 hasConcept C154945302 @default.
• W4312479381 hasConcept C17744445 @default.
• W4312479381 hasConcept C199539241 @default.
• W4312479381 hasConcept C2776151529 @default.
• W4312479381 hasConcept C2776359362 @default.
• W4312479381 hasConcept C2776401178 @default.
• W4312479381 hasConcept C2781238097 @default.
• W4312479381 hasConcept C41008148 @default.
• W4312479381 hasConcept C41895202 @default.
• W4312479381 hasConcept C52622490 @default.
• W4312479381 hasConcept C81363708 @default.
• W4312479381 hasConcept C94625758 @default.
• W4312479381 hasConceptScore W4312479381C138885662 @default.
• W4312479381 hasConceptScore W4312479381C153180895 @default.
• W4312479381 hasConceptScore W4312479381C154945302 @default.
• W4312479381 hasConceptScore W4312479381C17744445 @default.
• W4312479381 hasConceptScore W4312479381C199539241 @default.
• W4312479381 hasConceptScore W4312479381C2776151529 @default.
• W4312479381 hasConceptScore W4312479381C2776359362 @default.

• next