activity
20162025
most citednuts-flow/ml: data pre-processing for deep learning

8 citations · 11 across the 11 of their papers we have counts for

collaborators

15 papers

cs.CE2025

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…

cs.CV2024

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…

cs.CV2023

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…

cs.CV2023

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…

cs.LG2022

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…

cs.CV2022

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…