Suranga Seneviratne — accepted AI-conference papers

2026

RankOOD - Class Ranking-based Out-of-Distribution Detection

Dishanika Denipitiyage, Naveen Karunanayake, Suranga Seneviratne, Sanjay Chawla

CVPR 2026

We propose RankOOD, a rank-based Out-of-Distribution (OOD) detection approach based on training a model with the Placket-Luce loss, which is now extensively used for preference alignment tasks in foundational models. Our approach is based on the insight that with a deep learning model trained using

Cited by 0 Source ↗Scholar ↗

2019

DeepCaps: Going Deeper With Capsule Networks

Jathushan Rajasegaran, Vinoj Jayasundara, Sandaru Jayasekara, Hirunima Jayasekara, Suranga Seneviratne, Ranga Rodrigo

CVPR 2019oral

Capsule Network is a promising concept in deep learning, yet its true potential is not fully realized thus far, providing sub-par performance on several key benchmark datasets with complex data. Drawing intuition from the success achieved by Convolutional Neural Networks (CNNs) by going deeper, we i…

Cited by 312 PDF ↗code ↗Scholar ↗