S
Sudanthi Wijewickrema
Researcher at University of Melbourne
Publications - 66
Citations - 1541
Sudanthi Wijewickrema is an academic researcher from University of Melbourne. The author has contributed to research in topics: Artificial neural network & Image segmentation. The author has an hindex of 12, co-authored 63 publications receiving 1160 citations. Previous affiliations of Sudanthi Wijewickrema include Monash University & Monash University, Clayton campus.
Papers
More filters
Posted Content
Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality
Xingjun Ma,Bo Li,Yisen Wang,Sarah M. Erfani,Sudanthi Wijewickrema,Grant Schoenebeck,Dawn Song,Michael E. Houle,James Bailey +8 more
TL;DR: The analysis of the LID characteristic for adversarial regions not only motivates new directions of effective adversarial defense, but also opens up more challenges for developing new attacks to better understand the vulnerabilities of DNNs.
Proceedings Article
Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality
Xingjun Ma,Bo Li,Yisen Wang,Sarah M. Erfani,Sudanthi Wijewickrema,Grant Schoenebeck,Dawn Song,Michael E. Houle,James Bailey +8 more
TL;DR: In this article, the dimensional properties of adversarial regions are characterized via the use of Local Intrinsic Dimensionality (LID), which assesses the space-filling capability of the region surrounding a reference example, based on the distance distribution of the example to its neighbors.
Proceedings Article
Dimensionality-Driven Learning with Noisy Labels
Xingjun Ma,Yisen Wang,Michael E. Houle,Shuo Zhou,Sarah M. Erfani,Shu-Tao Xia,Sudanthi Wijewickrema,James Bailey +7 more
TL;DR: This work proposes a new perspective for understanding DNN generalization for such datasets, by investigating the dimensionality of the deep representation subspace of training samples, and develops a new dimensionality-driven learning strategy that can effectively learn low-dimensional local subspaces that capture the data distribution.
Posted Content
Dimensionality-Driven Learning with Noisy Labels
Xingjun Ma,Yisen Wang,Michael E. Houle,Shuo Zhou,Sarah M. Erfani,Shu-Tao Xia,Sudanthi Wijewickrema,James Bailey +7 more
TL;DR: In this article, the authors investigate the dimensionality of the deep representation subspace of training samples and develop a new dimensionality-driven learning strategy to adapt the loss function accordingly.
Journal ArticleDOI
Developing Effective Automated Feedback in Temporal Bone Surgery Simulation
Sudanthi Wijewickrema,Patorn Piromchai,Yun Zhou,Ioanna Ioannou,James Bailey,Gregor Kennedy,Stephen O'Leary +6 more
TL;DR: The automated feedback system was observed to be effective in improving surgical technique, and the provided feedback was found to be accurate and useful.