FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3192731655> ?p ?o ?g. }

• W3192731655 endingPage "2965" @default.
• W3192731655 startingPage "2965" @default.
• W3192731655 abstract "Machine learning, particularly deep learning (DL), has become a central and state-of-the-art method for several computer vision applications and remote sensing (RS) image processing. Researchers are continually trying to improve the performance of the DL methods by developing new architectural designs of the networks and/or developing new techniques, such as attention mechanisms. Since the attention mechanism has been proposed, regardless of its type, it has been increasingly used for diverse RS applications to improve the performances of the existing DL methods. However, these methods are scattered over different studies impeding the selection and application of the feasible approaches. This study provides an overview of the developed attention mechanisms and how to integrate them with different deep learning neural network architectures. In addition, it aims to investigate the effect of the attention mechanism on deep learning-based RS image processing. We identified and analyzed the advances in the corresponding attention mechanism-based deep learning (At-DL) methods. A systematic literature review was performed to identify the trends in publications, publishers, improved DL methods, data types used, attention types used, overall accuracies achieved using At-DL methods, and extracted the current research directions, weaknesses, and open problems to provide insights and recommendations for future studies. For this, five main research questions were formulated to extract the required data and information from the literature. Furthermore, we categorized the papers regarding the addressed RS image processing tasks (e.g., image classification, object detection, and change detection) and discussed the results within each group. In total, 270 papers were retrieved, of which 176 papers were selected according to the defined exclusion criteria for further analysis and detailed review. The results reveal that most of the papers reported an increase in overall accuracy when using the attention mechanism within the DL methods for image classification, image segmentation, change detection, and object detection using remote sensing images." @default.
• W3192731655 created "2021-08-16" @default.
• W3192731655 creator A5002683918 @default.
• W3192731655 creator A5069826864 @default.
• W3192731655 creator A5086176346 @default.
• W3192731655 creator A5086426963 @default.
• W3192731655 date "2021-07-28" @default.
• W3192731655 modified "2023-10-18" @default.
• W3192731655 title "Effect of Attention Mechanism in Deep Learning-Based Remote Sensing Image Processing: A Systematic Literature Review" @default.
• W3192731655 cites W2073632844 @default.
• W3192731655 cites W2074102825 @default.
• W3192731655 cites W2085323753 @default.
• W3192731655 cites W2106956101 @default.
• W3192731655 cites W2111256709 @default.
• W3192731655 cites W2112845172 @default.
• W3192731655 cites W2128272608 @default.
• W3192731655 cites W2261059368 @default.
• W3192731655 cites W2412588858 @default.
• W3192731655 cites W2474462684 @default.
• W3192731655 cites W2534925027 @default.
• W3192731655 cites W2567285691 @default.
• W3192731655 cites W2648242067 @default.
• W3192731655 cites W2782522152 @default.
• W3192731655 cites W2804532080 @default.
• W3192731655 cites W2890732922 @default.
• W3192731655 cites W2897246379 @default.
• W3192731655 cites W2897283027 @default.
• W3192731655 cites W2900094710 @default.
• W3192731655 cites W2900147932 @default.
• W3192731655 cites W2920964209 @default.
• W3192731655 cites W2937675449 @default.
• W3192731655 cites W2937933649 @default.
• W3192731655 cites W2940726923 @default.
• W3192731655 cites W2942170965 @default.
• W3192731655 cites W2944418962 @default.
• W3192731655 cites W2944971001 @default.
• W3192731655 cites W2945127520 @default.
• W3192731655 cites W2963006576 @default.
• W3192731655 cites W2963064196 @default.
• W3192731655 cites W2963420686 @default.
• W3192731655 cites W2964164961 @default.
• W3192731655 cites W2969238677 @default.
• W3192731655 cites W2972081044 @default.
• W3192731655 cites W2973777195 @default.
• W3192731655 cites W2974373385 @default.
• W3192731655 cites W2975331005 @default.
• W3192731655 cites W2980881023 @default.
• W3192731655 cites W2981266721 @default.
• W3192731655 cites W2981895542 @default.
• W3192731655 cites W2983376237 @default.
• W3192731655 cites W2989218065 @default.
• W3192731655 cites W2989871747 @default.
• W3192731655 cites W2991286101 @default.
• W3192731655 cites W2992172495 @default.
• W3192731655 cites W2994033677 @default.
• W3192731655 cites W2994681282 @default.
• W3192731655 cites W2997150065 @default.
• W3192731655 cites W2997597702 @default.
• W3192731655 cites W3003295287 @default.
• W3192731655 cites W3003397706 @default.
• W3192731655 cites W3003882269 @default.
• W3192731655 cites W3004423752 @default.
• W3192731655 cites W3004732939 @default.
• W3192731655 cites W3004916592 @default.
• W3192731655 cites W3009942016 @default.
• W3192731655 cites W3011515952 @default.
• W3192731655 cites W3016174083 @default.
• W3192731655 cites W3017622525 @default.
• W3192731655 cites W3019448917 @default.
• W3192731655 cites W3022548607 @default.
• W3192731655 cites W3026300872 @default.
• W3192731655 cites W3026889349 @default.
• W3192731655 cites W3028448552 @default.
• W3192731655 cites W3031015423 @default.
• W3192731655 cites W3031696400 @default.
• W3192731655 cites W3031696893 @default.
• W3192731655 cites W3032837604 @default.
• W3192731655 cites W3032940603 @default.
• W3192731655 cites W3036679688 @default.
• W3192731655 cites W3038833292 @default.
• W3192731655 cites W3041525128 @default.
• W3192731655 cites W3041614910 @default.
• W3192731655 cites W3042203953 @default.
• W3192731655 cites W3043181422 @default.
• W3192731655 cites W3043183554 @default.
• W3192731655 cites W3043257208 @default.
• W3192731655 cites W3045918052 @default.
• W3192731655 cites W3046109728 @default.
• W3192731655 cites W3047238784 @default.
• W3192731655 cites W3048029844 @default.
• W3192731655 cites W3048447490 @default.
• W3192731655 cites W3049361954 @default.
• W3192731655 cites W3049736620 @default.
• W3192731655 cites W3064134516 @default.
• W3192731655 cites W3080988368 @default.
• W3192731655 cites W3081119210 @default.
• W3192731655 cites W3082183666 @default.
• W3192731655 cites W3083219173 @default.

• next