TY - JOUR
T1 - Uncertainty-Aware Graph Reasoning with Global Collaborative Learning for Remote Sensing Salient Object Detection
AU - Liu, Yanfeng
AU - Yuan, Yuan
AU - Wang, Qi
N1 - Publisher Copyright:
© 2004-2012 IEEE.
PY - 2023
Y1 - 2023
N2 - Recently, fully convolutional networks (FCNs) have contributed significantly to salient object detection (SOD) in optical remote sensing images (RSIs). However, owing to the limited receptive fields of FCNs, accurate and integral detection of salient objects in RSIs with complex edges and irregular topology is still challenging. Moreover, suffering from the low contrast and complicated background of RSIs, existing models often occur ambiguous or uncertain recognition. To remedy the above problems, we propose a novel hybrid modeling approach, i.e., uncertainty-aware graph reasoning with global collaborative learning (UG2L) framework. Specifically, we propose a graph reasoning pipeline to model the intricate relations among RSI patches instead of pixels and introduce an efficient graph reasoning block (GRB) to build graph representations. On top of it, a global context block (GCB) with a linear attention mechanism is proposed to explore the multiscale and global context collaboratively. Finally, we design a simple yet effective uncertainty-aware loss (UAL) to enhance the model's reliability for better prediction of saliency or nonsaliency. Experimental and visual results on three datasets show the superiority of the proposed UG2L. Code is available at https://github.com/lyf0801/UG2L.
AB - Recently, fully convolutional networks (FCNs) have contributed significantly to salient object detection (SOD) in optical remote sensing images (RSIs). However, owing to the limited receptive fields of FCNs, accurate and integral detection of salient objects in RSIs with complex edges and irregular topology is still challenging. Moreover, suffering from the low contrast and complicated background of RSIs, existing models often occur ambiguous or uncertain recognition. To remedy the above problems, we propose a novel hybrid modeling approach, i.e., uncertainty-aware graph reasoning with global collaborative learning (UG2L) framework. Specifically, we propose a graph reasoning pipeline to model the intricate relations among RSI patches instead of pixels and introduce an efficient graph reasoning block (GRB) to build graph representations. On top of it, a global context block (GCB) with a linear attention mechanism is proposed to explore the multiscale and global context collaboratively. Finally, we design a simple yet effective uncertainty-aware loss (UAL) to enhance the model's reliability for better prediction of saliency or nonsaliency. Experimental and visual results on three datasets show the superiority of the proposed UG2L. Code is available at https://github.com/lyf0801/UG2L.
KW - Global collaborative learning
KW - graph reasoning
KW - optical remote sensing image (RSI)
KW - salient object detection (SOD)
KW - uncertainty-aware loss (UAL)
UR - http://www.scopus.com/inward/record.url?scp=85166276409&partnerID=8YFLogxK
U2 - 10.1109/LGRS.2023.3299245
DO - 10.1109/LGRS.2023.3299245
M3 - 文章
AN - SCOPUS:85166276409
SN - 1545-598X
VL - 20
JO - IEEE Geoscience and Remote Sensing Letters
JF - IEEE Geoscience and Remote Sensing Letters
M1 - 6008105
ER -