103 citations · 182 across the 14 of their papers we have counts for
16 papers
The Tilt of the Velocity Ellipsoid in the Milky Way Disk with GALAH-Gaia Data
Zhenzhen He, Ruilan Yang, Hui Li +1
We investigate the metallicity dependence of the tilt of the velocity ellipsoid using more than 572,000 stars selected from GALAH and Gaia. We find that the tilt angles of disk sta…
Metric Unreliability in Multimodal Machine Unlearning: A Systematic Analysis and Principled Unified Score
Abdullah Ahmad Khan, Hamid Laga, Ferdous Sohel
Machine unlearning in Vision-Language Models (VLMs) is required for compliance with the General Data Protection Regulation (GDPR), yet current evaluation practices are inconsistent…
DurableUn: Quantization-Induced Recovery Attacks in Machine Unlearning
Abdullah Ahmad Khan, Ferdous Sohel
Machine unlearning aims to remove specified training data to satisfy privacy regulations such as GDPR. However, existing evaluations assume identical precision at unlearning and de…
Certified vs. Empirical Adversarial Robust-ness via Hybrid Convolutions with Attention Stochasticity
Joy Dhar, Song Xia, Manish Kumar Pandey +5
We introduce Hybrid Convolutions with Attention Stochasticity (HyCAS), an adversarial defense that narrows the long-standing gap between provable robustness under L2 certificates a…
MultiShadow: Multi-Object Shadow Generation for Image Compositing via Diffusion Model
Waqas Ahmed, Dean Diepeveen, Ferdous Sohel
Realistic shadow generation is crucial for achieving seamless image compositing, yet existing methods primarily focus on single-object insertion and often fail to generalize when m…
GNF: Gaussian Neural Fields for Multidimensional Signal Representation and Reconstruction
Abdelaziz Bouzidi, Hamid Laga, Hazem Wannous +1
Neural fields have emerged as a powerful framework for representing continuous multidimensional signals such as images and videos, 3D and 4D objects and scenes, and radiance fields…
Weed Recognition using Deep Learning Techniques on Class-imbalanced Imagery
A S M Mahmudul Hasan, Ferdous Sohel, Dean Diepeveen +2
Most weed species can adversely impact agricultural productivity by competing for nutrients required by high-value crops. Manual weeding is not practical for large cropping areas.…
A Survey of Deep Learning Techniques for Weed Detection from Images
A S M Mahmudul Hasan, Ferdous Sohel, Dean Diepeveen +2
The rapid advances in Deep Learning (DL) techniques have enabled rapid detection, localisation, and recognition of objects from images or videos. DL techniques are now being used i…
Bidirectional Mapping Coupled GAN for Generalized Zero-Shot Learning
Tasfia Shermin, Shyh Wei Teng, Ferdous Sohel +2
Bidirectional mapping-based generalized zero-shot learning (GZSL) methods rely on the quality of synthesized features to recognize seen and unseen data. Therefore, learning a joint…
Imputation of Missing Data with Class Imbalance using Conditional Generative Adversarial Networks
Saqib Ejaz Awan, Mohammed Bennamoun, Ferdous Sohel +2
Missing data is a common problem faced with real-world datasets. Imputation is a widely used technique to estimate the missing data. State-of-the-art imputation approaches, such as…
RCNN for Region of Interest Detection in Whole Slide Images
A Nugaliyadde, Kok Wai Wong, Jeremy Parry +5
Digital pathology has attracted significant attention in recent years. Analysis of Whole Slide Images (WSIs) is challenging because they are very large, i.e., of Giga-pixel resolut…
Adversarial Network with Multiple Classifiers for Open Set Domain Adaptation
Tasfia Shermin, Guojun Lu, Shyh Wei Teng +2
Domain adaptation aims to transfer knowledge from a domain with adequate labeled samples to a domain with scarce labeled samples. Prior research has introduced various open set dom…
Robust Image Classification Using A Low-Pass Activation Function and DCT Augmentation
Md Tahmid Hossain, Shyh Wei Teng, Ferdous Sohel +1
Convolutional Neural Network's (CNN's) performance disparity on clean and corrupted datasets has recently come under scrutiny. In this work, we analyse common corruptions in the fr…
Unconstrained Matching of 2D and 3D Descriptors for 6-DOF Pose Estimation
Uzair Nadeem, Mohammed Bennamoun, Roberto Togneri +1
This paper proposes a novel concept to directly match feature descriptors extracted from 2D images with feature descriptors extracted from 3D point clouds. We use this concept to d…
Robust Pose Invariant Shape and Texture based Hand Recognition
F. Sohel, A. El-Sallam, M. Bennamoun
This paper presents a novel personal identification and verification system using information extracted from the hand shape and texture. The system has two major constituent module…
Automatic Hierarchical Classification of Kelps using Deep Residual Features
Ammar Mahmood, Ana Giraldo Ospina, Mohammed Bennamoun +6
Across the globe, remote image data is rapidly being collected for the assessment of benthic communities from shallow to extremely deep waters on continental slopes to the abyssal…