Realigned softmax warping for deep metric learning
MG DeMoor, JJ Prevost - arXiv preprint arXiv:2408.15656, 2024 - arxiv.org
Deep Metric Learning (DML) loss functions traditionally aim to control the forces of
separability and compactness within an embedding space so that the same class data …
separability and compactness within an embedding space so that the same class data …
Adaptive Fourier Convolution Network for Road Segmentation in Remote Sensing Images
H Liu, C Wang, J Zhao, S Chen… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Segmentation of roads in remote sensing (RS) images is a challenging task due to the
inhomogeneous intensity, nonconsistent contrast, and very cluttered background in remote …
inhomogeneous intensity, nonconsistent contrast, and very cluttered background in remote …
Deep metric learning with chance constraints
Deep metric learning (DML) aims to minimize empirical expected loss of the pairwise intra-
/inter-class proximity violations in the embedding space. We relate DML to feasibility …
/inter-class proximity violations in the embedding space. We relate DML to feasibility …
Realigned Softmax Warping for Compact and Separable Embedding Formation
MG DeMoor - 2024 - search.proquest.com
Abstract Deep Metric Learning (DML) loss functions traditionally aim to control the forces of
separability and compactness within an embedding space so that the same class data …
separability and compactness within an embedding space so that the same class data …