13 citations · 21 across the 14 of their papers we have counts for
12 papers · 1 filter
Leak-Free Cross-Validated Stacking with Per-Architecture Calibration for Sand-Boil Segmentation in Earthen Levees
Padam Jung Thapa, Anav Katwal, Ayon Dey +4
Sand boils, points where water seeping beneath an earthen levee re-emerges at the surface, are early warnings of internal erosion, and deep segmentation networks are increasingly u…
EfficientPENet: Real-Time Depth Completion from Sparse LiDAR via Lightweight Multi-Modal Fusion
Johny J. Lopez, Md Meftahul Ferdaus, Mahdi Abdelguerfi +4
Depth completion from sparse LiDAR measurements and corresponding RGB images is a prerequisite for accurate 3D perception in robotic systems. Existing methods achieve high accuracy…
VeloxNet: Efficient Spatial Gating for Lightweight Embedded Image Classification
Md Meftahul Ferdaus, Elias Ioup, Mahdi Abdelguerfi +4
Deploying deep learning models on embedded devices for tasks such as aerial disaster monitoring and infrastructure inspection requires architectures that balance accuracy with stri…
Attention-Enhanced Prototypical Learning for Few-Shot Infrastructure Defect Segmentation
Christina Thrainer, Md Meftahul Ferdaus, Mahdi Abdelguerfi +4
Few-shot semantic segmentation is vital for deep learning-based infrastructure inspection applications, where labeled training examples are scarce and expensive. Although existing…
KARMA: Efficient Structural Defect Segmentation via Kolmogorov-Arnold Representation Learning
Md Meftahul Ferdaus, Mahdi Abdelguerfi, Elias Ioup +3
Semantic segmentation of structural defects in civil infrastructure remains challenging due to variable defect appearances, harsh imaging conditions, and significant class imbalanc…
Few-Shot Learning in Video and 3D Object Detection: A Survey
Md Meftahul Ferdaus, Kendall N. Niles, Joe Tom +2
Few-shot learning (FSL) enables object detection models to recognize novel classes given only a few annotated examples, thereby reducing expensive manual data labeling. This survey…
FORTRESS: Function-composition Optimized Real-Time Resilient Structural Segmentation via Kolmogorov-Arnold Enhanced Spatial Attention Networks
Christina Thrainer, Md Meftahul Ferdaus, Mahdi Abdelguerfi +4
Automated structural defect segmentation in civil infrastructure faces a critical challenge: achieving high accuracy while maintaining computational efficiency for real-time deploy…
KANICE: Kolmogorov-Arnold Networks with Interactive Convolutional Elements
Md Meftahul Ferdaus, Mahdi Abdelguerfi, Elias Ioup +4
We introduce KANICE (Kolmogorov-Arnold Networks with Interactive Convolutional Elements), a novel neural architecture that combines Convolutional Neural Networks (CNNs) with Kolmog…
Imbalance-Aware Culvert-Sewer Defect Segmentation Using an Enhanced Feature Pyramid Network
Rasha Alshawi, Md Meftahul Ferdaus, Mahdi Abdelguerfi +3
Imbalanced datasets are a significant challenge in real-world scenarios. They lead to models that underperform on underrepresented classes, which is a critical issue in infrastruct…
SHARP-Net: A Refined Pyramid Network for Deficiency Segmentation in Culverts and Sewer Pipes
Rasha Alshawi, Md Meftahul Ferdaus, Md Tamjidul Hoque +4
This paper introduces Semantic Haar-Adaptive Refined Pyramid Network (SHARP-Net), a novel architecture for semantic segmentation. SHARP-Net integrates a bottom-up pathway featuring…
Dual Attention U-Net with Feature Infusion: Pushing the Boundaries of Multiclass Defect Segmentation
Rasha Alshawi, Md Tamjidul Hoque, Md Meftahul Ferdaus +7
The proposed architecture, Dual Attentive U-Net with Feature Infusion (DAU-FI Net), addresses challenges in semantic segmentation, particularly on multiclass imbalanced datasets wi…
Dual-Stream Attention Transformers for Sewer Defect Classification
Abdullah Al Redwan Newaz, Mahdi Abdeldguerfi, Kendall N. Niles +1
We propose a dual-stream multi-scale vision transformer (DS-MSHViT) architecture that processes RGB and optical flow inputs for efficient sewer defect classification. Unlike existi…