Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal Scientific Journal of Engineering Research
Beruwalage, Shehan Maxwell
Unknown Affiliation
Engineering

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
LSKD: Lightweight Self-Knowledge Distillation Framework for Fast and Robust Crowd Counting Raza, Muhammad; Ling, Miaogen; Ur Rahman, Atta; Pallewatta, Pandula; Hersi, Aboubakar Abdinur; Beruwalage, Shehan Maxwell; Kannangara, Deshan Sachintha
Scientific Journal of Engineering Research Vol. 2 No. 2 (2026): June
Publisher : PT. Teknologi Futuristik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64539/sjer.v2i2.2026.436

Abstract

Crowd counting plays an important role in the surveillance of the safety of the people, traffic, and intelligent surveillance systems. However, the exact density estimations remain hard to achieve in highly congested scenes due to the tough occlusion, large-scale variance, and complicated background. Although the recent deep-learning methods have high performance, several of them do not need computationally efficient underlying backbone networks, and rather, they employ an external teacher-student distillation architecture, which can limit their use in resource-constrained applications. To avoid this problem, we introduce LSKD, a lightweight self-knowledge distillation network that is density map regression-specific. Unlike other conventional teacher-dependent processes, LSKD can also independently carry out internal multi-level feature alignment within a single small network that is not in need of an external teacher model. The structure integrates a Feature Matching Block (FMB) and a Context Fusion (CoFuse) block to enhance the hierarchical match of features and global awareness of context. The large experiments demonstrate that LSKD obtain competitive performance using the number of parameters as 2.65 million and GFLOPs as 10.23. Particularly, it has 63.17 MAE on ShanghaiTech Part A, 8.94 on ShanghaiTech Part B, 143.7 on UCF-QNRF, and 223.88 on UCF-CC-50, which is a good ratio between the accuracy and the efficiency of the calculations. Such results indicate that LSKD has an implementable and efficient solution to the real-time counting of crowds at the edge devices.
Parameter-Efficient Fine-Tuning for Sonar Shipwreck Segmentation: A Seed Averaged Study with SegFormer and LoRA Beruwalage, Shehan Maxwell; Yin, Chunyong; Raza, Muhammad; Kannangara, Deshan Sachintha; Hendavitharana, Sachini Amani
Scientific Journal of Engineering Research Vol. 2 No. 2 (2026): June
Publisher : PT. Teknologi Futuristik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64539/sjer.v2i2.2026.454

Abstract

Accurate segmentation of shipwreck targets in sonar imagery is important for underwater archaeology, marine monitoring, and search operations, but the task remains difficult because labeled sonar masks are scarce and full adaptation of transformer models can be computationally expensive. This study evaluates whether parameter-efficient fine-tuning can provide a practical alternative for binary sonar shipwreck segmentation. Using SegFormer-B0 initialized from a pretrained checkpoint, three adaptation strategies were compared under a consistent protocol: full fine-tuning of all model parameters (FullFT), training only the segmentation head (Head-only), and LoRA-based adaptation of selected linear layers together with head training (LoRA-A+Head). Models were selected by the best validation epoch and evaluated on a held-out test set. Across three random seeds, FullFT achieved the best performance, with a Dice score of 0.614 ± 0.008 and IoU of 0.487 ± 0.007. LoRA-A+Head achieved a Dice score of 0.546 ± 0.010 and IoU of 0.401 ± 0.008 while updating only 1.57% of the parameters, whereas Head-only reached 0.494 ± 0.010 Dice and 0.354 ± 0.008 IoU. These results show a clear accuracy efficiency trade off, full fine-tuning gives the highest accuracy, whereas LoRA-A+Head offers a practical option when reducing the number of updated parameters is important. The findings support the use of parameter-efficient adaptation for sonar segmentation in compute-limited settings.
Co-Authors Chunyong Yin Hendavitharana, Sachini Amani Hersi, Aboubakar Abdinur Kannangara, Deshan Sachintha Ling, Miaogen Pallewatta, Pandula Raza, Muhammad Ur Rahman, Atta