Stochastic class-based hard example mining for deep metric learning

Y Suh, B Han, W Kim, KM Lee - Proceedings of the IEEE …, 2019 - openaccess.thecvf.com
Performance of deep metric learning depends heavily on the capability of mining hard
negative examples during training. However, many metric learning algorithms often require …

Spectral, probabilistic, and deep metric learning: Tutorial and survey

B Ghojogh, A Ghodsi, F Karray, M Crowley - arxiv preprint arxiv …, 2022 - arxiv.org
This is a tutorial and survey paper on metric learning. Algorithms are divided into spectral,
probabilistic, and deep metric learning. We first start with the definition of distance metric …

Semi-supervised multi-view deep discriminant representation learning

X Jia, XY **g, X Zhu, S Chen, B Du… - IEEE transactions on …, 2020 - ieeexplore.ieee.org
Learning an expressive representation from multi-view data is a key step in various real-
world applications. In this paper, we propose a semi-supervised multi-view deep …

Primitivenet: Primitive instance segmentation with local primitive embedding under adversarial metric

J Huang, Y Zhang, M Sun - Proceedings of the IEEE/CVF …, 2021 - openaccess.thecvf.com
We present PrimitiveNet, a novel approach for high-resolution primitive instance
segmentation from point clouds on a large scale. Our key idea is to transform the global …

Linearity-aware subspace clustering

Y Xu, S Chen, J Li, J Qian - Proceedings of the AAAI conference on …, 2022 - ojs.aaai.org
Obtaining a good similarity matrix is extremely important in subspace clustering. Current
state-of-the-art methods learn the similarity matrix through self-expressive strategy …

Curvilinear distance metric learning

S Chen, L Luo, J Yang, C Gong, J Li… - Advances in Neural …, 2019 - proceedings.neurips.cc
Abstract Distance Metric Learning aims to learn an appropriate metric that faithfully
measures the distance between two data points. Traditional metric learning methods usually …

Unsupervised deep metric learning via orthogonality based probabilistic loss

UK Dutta, M Harandi, CC Sekhar - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
Metric learning is an important problem in machine learning. It aims to group similar
observations together. Existing state-of-the-art metric learning approaches require class …

Adversarial similarity metric learning for kinship verification

Z Wei, M Xu, L Geng, H Liu, H Yin - IEEE Access, 2019 - ieeexplore.ieee.org
Given a pair of facial images, it is an interesting yet challenging problem to determine if there
is a kin relation between them. Recent research on that topic has made encouraging …

On the robustness of metric learning: an adversarial perspective

M Huai, T Zheng, C Miao, L Yao, A Zhang - ACM Transactions on …, 2022 - dl.acm.org
Metric learning aims at automatically learning a distance metric from data so that the precise
similarity between data instances can be faithfully reflected, and its importance has long …

Time-frequency deep metric learning for multivariate time series classification

Z Chen, Y Liu, J Zhu, Y Zhang, R **, X He, J Tao… - Neurocomputing, 2021 - Elsevier
Multivariate time series (MTS) data exist in various fields of studies and MTS classification is
an important research topic in the machine learning community. Researchers have …