An overview of deep learning architectures in few-shot learning domain
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 …
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
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 …
in the standard regime of rich training data and in the few-shot scenario, where each …
Calibrated prediction intervals for neural network regressors
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 …
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
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 …
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
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 …
grasping and manipulation in warehouses or smart factories. Deep convolutional neural …
Scaling speech enhancement in unseen environments with noise embeddings
We address the problem of speech enhancement generalisation to unseen environments by
performing two manipulations. First, we embed an additional recording from the environment …
performing two manipulations. First, we embed an additional recording from the environment …
Transfer learning: Domain adaptation
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 …
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 …
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 …
amounts of training data and cannot deal with unseen classes of objects well. In this paper …