An overview of deep learning architectures in few-shot learning domain

S Jadon, A Jadon - arXiv preprint arXiv:2008.06365, 2020 - arxiv.org
Since 2012, Deep learning has revolutionized Artificial Intelligence and has achieved state-
of-the-art outcomes in different domains, ranging from Image Classification to Speech …

Repmet: Representative-based metric learning for classification and few-shot object detection

L Karlinsky, J Shtok, S Harary… - Proceedings of the …, 2019 - openaccess.thecvf.com
Distance metric learning (DML) has been successfully applied to object classification, both
in the standard regime of rich training data and in the few-shot scenario, where each …

Calibrated prediction intervals for neural network regressors

G Keren, N Cummins, B Schuller - IEEE Access, 2018 - ieeexplore.ieee.org
Ongoing developments in neural network models are continually advancing the state-of-the-
art in terms of system accuracy. However, the predicted labels should not be regarded as the …

[PDF][PDF] Repmet: Representative-based metric learning for classification and one-shot object detection

E Schwartz, L Karlinsky, J Shtok, S Harary… - arXiv preprint arXiv …, 2018 - researchgate.net
Distance metric learning (DML) has been successfully applied to object classification, both
in the standard regime of rich training data and in the few-shot scenario, where each …

Fully convolutional one-shot object segmentation for industrial robotics

B Schnieders, S Luo, G Palmer, K Tuyls - arXiv preprint arXiv:1903.00683, 2019 - arxiv.org
The ability to identify and localize new objects robustly and effectively is vital for robotic
grasping and manipulation in warehouses or smart factories. Deep convolutional neural …

Scaling speech enhancement in unseen environments with noise embeddings

G Keren, J Han, B Schuller - arXiv preprint arXiv:1810.12757, 2018 - arxiv.org
We address the problem of speech enhancement generalisation to unseen environments by
performing two manipulations. First, we embed an additional recording from the environment …

Transfer learning: Domain adaptation

U Kamath, J Liu, J Whitaker, U Kamath, J Liu… - Deep learning for NLP …, 2019 - Springer
Abstract Domain adaptation is a form of transfer learning, in which the task remains the
same, but there is a domain shift or a distribution change between the source and the target …

[PDF][PDF] Neural network supervision: Notes on loss functions, labels and confidence estimation

G Keren - 2020 - opus4.kobv.de
We consider a number of enhancements to the standard neural network training paradigm.
First, we show that carefully designed parameter update rules may replace the need for a …

A New Learning-Based One Shot Detection Framework for Natural Images

S Na, R Yan - Artificial Neural Networks and Machine Learning …, 2019 - Springer
Nowadays, existing object detection methods based on deep learning usually need vast
amounts of training data and cannot deal with unseen classes of objects well. In this paper …