19 citations · 34 across the 20 of their papers we have counts for
21 papers
Weakly Supervised Concept Learning with Class-Level Priors for Interpretable Medical Diagnosis
Md Nahiduzzaman, Steven Korevaar, Alireza Bab-Hadiashar +1
Human-interpretable predictions are essential for deploying AI in medical imaging, yet most interpretable-by-design (IBD) frameworks require concept annotations for training data,…
BiomedXPro: Prompt Optimization for Explainable Diagnosis with Biomedical Vision Language Models
Kaushitha Silva, Mansitha Eashwara, Sanduni Ubayasiri +2
The clinical adoption of biomedical vision-language models is hindered by prompt optimization techniques that produce either uninterpretable latent vectors or single textual prompt…
Uncertainty-Aware Information Pursuit for Interpretable and Reliable Medical Image Analysis
Md Nahiduzzaman, Steven Korevaar, Zongyuan Ge +3
To be adopted in safety-critical domains like medical image analysis, AI systems must provide human-interpretable decisions. Variational Information Pursuit (V-IP) offers an interp…
Automated Keypoint Estimation for Self-Piercing Rivet Joints Using micro-CT Imaging and Transfer Learning
Wei Qin Chuah, Ruwan Tennakoon, Amanda Freis +3
The structural integrity of self-piercing rivet (SPR) joints is critical in automotive industries, yet its evaluation poses challenges due to the limitations of traditional destruc…
Generalization Capabilities of Neural Cellular Automata for Medical Image Segmentation: A Robust and Lightweight Approach
Steven Korevaar, Ruwan Tennakoon, Alireza Bab-Hadiashar
In the field of medical imaging, the U-Net architecture, along with its variants, has established itself as a cornerstone for image segmentation tasks, particularly due to its stro…
Enhanced Online Test-time Adaptation with Feature-Weight Cosine Alignment
WeiQin Chuah, Ruwan Tennakoon, Alireza Bab-Hadiashar
Online Test-Time Adaptation (OTTA) has emerged as an effective strategy to handle distributional shifts, allowing on-the-fly adaptation of pre-trained models to new target domains…
Domain Generalization by Learning from Privileged Medical Imaging Information
Steven Korevaar, Ruwan Tennakoon, Ricky O'Brien +2
Learning the ability to generalize knowledge between similar contexts is particularly important in medical imaging as data distributions can shift substantially from one hospital t…
Single Domain Generalization via Normalised Cross-correlation Based Convolutions
WeiQin Chuah, Ruwan Tennakoon, Reza Hoseinnezhad +2
Deep learning techniques often perform poorly in the presence of domain shift, where the test data follows a different distribution than the training data. The most practically des…
IT-RUDA: Information Theory Assisted Robust Unsupervised Domain Adaptation
Shima Rashidi, Ruwan Tennakoon, Aref Miri Rekavandi +7
Distribution shift between train (source) and test (target) datasets is a common problem encountered in machine learning applications. One approach to resolve this issue is to use…
ITSA: An Information-Theoretic Approach to Automatic Shortcut Avoidance and Domain Generalization in Stereo Matching Networks
WeiQin Chuah, Ruwan Tennakoon, Reza Hoseinnezhad +2
State-of-the-art stereo matching networks trained only on synthetic data often fail to generalize to more challenging real data domains. In this paper, we attempt to unfold an impo…
Maximum Consensus by Weighted Influences of Monotone Boolean Functions
Erchuan Zhang, David Suter, Ruwan Tennakoon +4
Robust model fitting is a fundamental problem in computer vision: used to pre-process raw data in the presence of outliers. Maximisation of Consensus (MaxCon) is one of the most po…
Robust Pooling through the Data Mode
Ayman Mukhaimar, Ruwan Tennakoon, Chow Yin Lai +2
The task of learning from point cloud data is always challenging due to the often occurrence of noise and outliers in the data. Such data inaccuracies can significantly influence t…
Achieving Domain Robustness in Stereo Matching Networks by Removing Shortcut Learning
WeiQin Chuah, Ruwan Tennakoon, Alireza Bab-Hadiashar +1
Learning-based stereo matching and depth estimation networks currently excel on public benchmarks with impressive results. However, state-of-the-art networks often fail to generali…
Consensus Maximisation Using Influences of Monotone Boolean Functions
Ruwan Tennakoon, David Suter, Erchuan Zhang +2
Consensus maximisation (MaxCon), which is widely used for robust fitting in computer vision, aims to find the largest subset of data that fits the model within some tolerance level…
Rotation Averaging with Attention Graph Neural Networks
Joshua Thorpe, Ruwan Tennakoon, Alireza Bab-Hadiashar
In this paper we propose a real-time and robust solution to large-scale multiple rotation averaging. Until recently, Multiple rotation averaging problem had been solved using conve…
Robust Object Classification Approach using Spherical Harmonics
Ayman Mukhaimar, Ruwan Tennakoon, Chow Yin Lai +2
In this paper, we present a robust spherical harmonics approach for the classification of point cloud-based objects. Spherical harmonics have been used for classification over the…
Adjusting Bias in Long Range Stereo Matching: A semantics guided approach
WeiQin Chuah, Ruwan Tennakoon, Reza Hoseinnezhad +2
Stereo vision generally involves the computation of pixel correspondences and estimation of disparities between rectified image pairs. In many applications, including simultaneous…
Monotone Boolean Functions, Feasibility/Infeasibility, LP-type problems and MaxCon
David Suter, Ruwan Tennakoon, Erchuan Zhang +2
This paper outlines connections between Monotone Boolean Functions, LP-Type problems and the Maximum Consensus Problem. The latter refers to a particular type of robust fitting cha…
nuts-flow/ml: data pre-processing for deep learning
S. Maetschke, R. Tennakoon, C. Vecchiola +1
Data preprocessing is a fundamental part of any machine learning application and frequently the most time-consuming aspect when developing a machine learning solution. Preprocessin…
Effective Sampling: Fast Segmentation Using Robust Geometric Model Fitting
Ruwan Tennakoon, Alireza Sadri, Reza Hoseinnezhad +1
Identifying the underlying models in a set of data points contaminated by noise and outliers, leads to a highly complex multi-model fitting problem. This problem can be posed as a…
Labeled Multi-Bernoulli Tracking for Industrial Mobile Platform Safety
Tharindu Rathnayake, Reza Hoseinnezhad, Ruwan Tennakoon +1
This paper presents a track-before-detect labeled multi-Bernoulli filter tailored for industrial mobile platform safety applications. We derive two application specific separable l…