Deep metric learning for few-shot image classification: A review of recent developments
Few-shot image classification is a challenging problem that aims to achieve the human level
of recognition based only on a small number of training images. One main solution to few …
of recognition based only on a small number of training images. One main solution to few …
Meta-learning control variates: Variance reduction with limited data
Control variates can be a powerful tool to reduce the variance of Monte Carlo estimators, but
constructing effective control variates can be challenging when the number of samples is …
constructing effective control variates can be challenging when the number of samples is …
Secure out-of-distribution task generalization with energy-based models
The success of meta-learning on out-of-distribution (OOD) tasks in the wild has proved to be
hit-and-miss. To safeguard the generalization capability of the meta-learned prior …
hit-and-miss. To safeguard the generalization capability of the meta-learned prior …
Hypershot: Few-shot learning by kernel hypernetworks
M Sendera, M Przewięźlikowski… - Proceedings of the …, 2023 - openaccess.thecvf.com
Few-shot models aim at making predictions using a minimal number of labeled examples
from a given task. The main challenge in this area is the one-shot setting where only one …
from a given task. The main challenge in this area is the one-shot setting where only one …
Bayesian active meta-learning for reliable and efficient AI-based demodulation
Two of the main principles underlying the life cycle of an artificial intelligence (AI) module in
communication networks are adaptation and monitoring. Adaptation refers to the need to …
communication networks are adaptation and monitoring. Adaptation refers to the need to …
Transductive decoupled variational inference for few-shot classification
A Singh, H Jamali-Rad - arXiv preprint arXiv:2208.10559, 2022 - arxiv.org
The versatility to learn from a handful of samples is the hallmark of human intelligence. Few-
shot learning is an endeavour to transcend this capability down to machines. Inspired by the …
shot learning is an endeavour to transcend this capability down to machines. Inspired by the …
Hypermaml: Few-shot adaptation of deep models with hypernetworks
M Przewięźlikowski, P Przybysz, J Tabor… - arXiv preprint arXiv …, 2022 - arxiv.org
The aim of Few-Shot learning methods is to train models which can easily adapt to
previously unseen tasks, based on small amounts of data. One of the most popular and …
previously unseen tasks, based on small amounts of data. One of the most popular and …
Learning to learn to demodulate with uncertainty quantification via bayesian meta-learning
Meta-learning, or learning to learn, offers a principled framework for few-shot learning. It
leverages data from multiple related learning tasks to infer an inductive bias that enables …
leverages data from multiple related learning tasks to infer an inductive bias that enables …
Single-sample finger vein recognition via competitive and progressive sparse representation
As an emerging biometric technology, finger vein recognition has attracted much attention in
recent years. However, single-sample recognition is a practical and longstanding challenge …
recent years. However, single-sample recognition is a practical and longstanding challenge …
Toward green and human-like artificial intelligence: A complete survey on contemporary few-shot learning approaches
Despite deep learning's widespread success, its data-hungry and computationally
expensive nature makes it impractical for many data-constrained real-world applications …
expensive nature makes it impractical for many data-constrained real-world applications …