Tuning a SAM-Based Model with Multi-Cognitive Visual Adapter to Remote Sensing Instance Segmentation

L Zheng, X Pu, F Xu - IEEE Journal of Selected Topics in …, 2024 - ieeexplore.ieee.org
The segment anything model (SAM), a foundational model designed for promptable
segmentation tasks, demonstrates exceptional generalization capabilities, making it highly …

ClassWise-SAM-adapter: Parameter efficient fine-tuning adapts segment anything to SAR domain for semantic segmentation

X Pu, H Jia, L Zheng, F Wang… - IEEE Journal of Selected …, 2025 - ieeexplore.ieee.org
In the realm of artificial intelligence, the emergence of foundation models, backed by high
computing capabilities and extensive data, has been revolutionary. Segment Anything Model (…

A Siamese Network-Based Similarity Measure for Target in SAR Images

L Zheng, Z Huang, Q Guo, X Pu… - IGARSS 2024-2024 IEEE …, 2024 - ieeexplore.ieee.org
Synthetic Aperture Radar (SAR) has been widely applied due to its capability for continuous
monitoring under all-weather and all-time conditions. Unlike optical images, targets in SAR …

Star generative adversarial VGG network-based sample augmentation for insulator defect detection

L Zhang, L Wang, Z Yan, Z Jia, H Wang… - International Journal of …, 2024 - Springer
Deep learning-based automated detection of insulator defects in electric power systems is a
critical technological challenge, pivotal for ensuring reliability and efficiency in the global …

Seismic fragility and loss estimation of self-centering steel braced frames under mainshock-aftershock sequences

C Fang, B Ping, Y Zheng, Y Ping, H Ling - Journal of Building Engineering, 2023 - Elsevier
This paper highlights the importance of considering local component failure of self-centering
braces (SCBs) when examining the seismic fragility and economic performance of …

Predicting reaction rate constants of organic compounds with oxidants in the atmospheric aqueous-phase through multi-task learning

L Gu, Z Chen - Atmospheric Environment, 2024 - Elsevier
The atmospheric aqueous-phase chemistry has received increasing attention in the last
decades for its non-negligible environmental significance. Yet, the insufficient experimental data …

Style alignment-based dynamic observation method for UAV-view geo-localization

J Shao, LH Jiang - IEEE Transactions on Geoscience and …, 2023 - ieeexplore.ieee.org
… The parameter size of our method is only 23.6M, which is similar to LPN, Vit-s, and Zheng,
but our AP value is much higher than these three methods. FSRA has the top results among …

Initial design and multi-objective optimization of four-product dividing wall column

Y Zheng, Z Wang, H Pan, H Ling - Separation and Purification Technology, 2023 - Elsevier
The numerous design alternatives and decision variables of four-product dividing wall column
(DWC) have presented significant challenges for its steady-state design. Therefore, this …

FCC coprocessing oil sands heavy gas oil and canola oil. 1. Yield structure

SH Ng, M Al-Sabawi, J Wang, H Ling, Y Zheng, Q Wei… - Fuel, 2015 - Elsevier
Reducing the carbon footprint or GHG emissions is a major challenge during the production
and processing of Canadian oil sands bitumen for clean transportation fuels. Co-processing …

Evaluation of multi-objective optimization methods applied to ternary dividing-wall columns

G Li, S Guan, Y Gao, W Liu, Y Zheng, H Pan… - … Research and Design, 2024 - Elsevier
Multi-objective optimization algorithms are widely employed in the optimization of Dividing-Wall
Column (DWC). However, due to the inherent complexity of DWC design problems, the …