1 code implementation • 19 Jan 2024 • Hanxun Huang, Ricardo J. G. B. Campello, Sarah Monazam Erfani, Xingjun Ma, Michael E. Houle, James Bailey
Representations learned via self-supervised learning (SSL) can be susceptible to dimensional collapse, where the learned representation subspace is of extremely low dimensionality and thus fails to represent the full data distribution and modalities.
1 code implementation • 10 Jan 2024 • Alastair Anderberg, James Bailey, Ricardo J. G. B. Campello, Michael E. Houle, Henrique O. Marques, Miloš Radovanović, Arthur Zimek
We present a nonparametric method for outlier detection that takes full account of local variations in intrinsic dimensionality within the dataset.
1 code implementation • 29 Sep 2022 • Laurent Amsaleg, Oussama Chelly, Michael E. Houle, Ken-ichi Kawarabayashi, Miloš Radovanović, Weeris Treeratanajaru
Accurate estimation of Intrinsic Dimensionality (ID) is of crucial importance in many data mining and machine learning tasks, including dimensionality reduction, outlier detection, similarity search and subspace clustering.
no code implementations • 15 Jul 2019 • Ruben Becker, Imane Hafnaoui, Michael E. Houle, Pan Li, Arthur Zimek
For each point, the recently-proposed Local Intrinsic Dimension (LID) model is used in identifying the axis directions along which features have the greatest local discriminability, or equivalently, the fewest number of components of LID that capture the local complexity of the data.
no code implementations • 2 May 2019 • Sukarna Barua, Xingjun Ma, Sarah Monazam Erfani, Michael E. Houle, James Bailey
In this paper, we demonstrate that an intrinsic dimensional characterization of the data space learned by a GAN model leads to an effective evaluation metric for GAN quality.
2 code implementations • ICML 2018 • Xingjun Ma, Yisen Wang, Michael E. Houle, Shuo Zhou, Sarah M. Erfani, Shu-Tao Xia, Sudanthi Wijewickrema, James Bailey
Datasets with significant proportions of noisy (incorrect) class labels present challenges for training accurate Deep Neural Networks (DNNs).
Ranked #39 on Image Classification on mini WebVision 1.0
1 code implementation • ICLR 2018 • Xingjun Ma, Bo Li, Yisen Wang, Sarah M. Erfani, Sudanthi Wijewickrema, Grant Schoenebeck, Dawn Song, Michael E. Houle, James Bailey
Deep Neural Networks (DNNs) have recently been shown to be vulnerable against adversarial examples, which are carefully crafted instances that can mislead DNNs to make errors during prediction.