Results 241 to 250 of about 514,020 (257)
Some of the next articles are maybe not open access.
2019 IEEE/CVF International Conference on Computer Vision (ICCV), 2019
We propose a variational Bayesian framework for enhancing few-shot learning performance. This idea is motivated by the fact that single point based metric learning approaches are inherently noise-vulnerable and easy-to-be-biased. In a nutshell, stochastic variational inference is invoked to approximate bias-eliminated class specific sample ...
Jian Zhang +4 more
openaire +1 more source
We propose a variational Bayesian framework for enhancing few-shot learning performance. This idea is motivated by the fact that single point based metric learning approaches are inherently noise-vulnerable and easy-to-be-biased. In a nutshell, stochastic variational inference is invoked to approximate bias-eliminated class specific sample ...
Jian Zhang +4 more
openaire +1 more source
IEEE Transactions on Neural Networks and Learning Systems
Forming deep feature embeddings is an effective method for few-shot learning (FSL). However, in the case of insufficient samples, overcoming the task complexity while improving the accuracy is still a major challenge. To address this problem, this article considers the consistency between similar data from the fractal perspective, introduces a priori ...
Fobao Zhou, Wenkai Huang
openaire +2 more sources
Forming deep feature embeddings is an effective method for few-shot learning (FSL). However, in the case of insufficient samples, overcoming the task complexity while improving the accuracy is still a major challenge. To address this problem, this article considers the consistency between similar data from the fractal perspective, introduces a priori ...
Fobao Zhou, Wenkai Huang
openaire +2 more sources
Personalized Federated Few-Shot Learning
IEEE Transactions on Neural Networks and Learning SystemsPersonalized federated learning (PFL) learns a personalized model for each client in a decentralized manner, where each client owns private data that are not shared and data among clients are non-independent and identically distributed (i.i.d.) However, existing PFL solutions assume that clients have sufficient training samples to jointly induce ...
Yunfeng Zhao +6 more
openaire +2 more sources
Secure collaborative few-shot learning
Knowledge-Based Systems, 2020Abstract Few-shot learning aims at training a model that can effectively recognize novel classes with extremely limited training examples. Few-shot learning via meta-learning can improve the performance on novel tasks by leveraging previously acquired knowledge as a prior when the training examples are extremely limited.
Yu Xie, Han Wang, Bin Yu, Chen Zhang
openaire +1 more source
Heterogeneous Riemannian Few-Shot Learning Network
IEEE Transactions on Neural Networks and Learning SystemsHow to learn and accurately distinguish new concepts from few samples, as humans do, is a long-standing concern in artificial intelligence (AI). Studies in brain science and neuroscience have shown that human brain perception is based on nonlinear manifolds, and high-dimensional manifolds can facilitate concept learning in neural circuits.
Jie Chen +7 more
openaire +2 more sources
A few shots at few shot learning
Automatic Target Recognition XXXIII, 2023Donald Waagen, Don Hulsey, David Gray
openaire +1 more source
Few-Shot Learning with Novelty Detection
Machine learning has achieved considerable success in data-intensive applications, yet encounters challenges when confronted with small datasets. Recently, few-shot learning (FSL) has emerged as a promising solution to address this limitation. By leveraging prior knowledge, FSL exhibits the ability to swiftly generalize to new tasks, even when ...Kim Bjerge +2 more
openaire +1 more source
Learning about few-shot concept learning
Nature Computational Science, 2022openaire +2 more sources
Co-Learning for Few-Shot Learning
Neural Processing Letters, 2022Rui Xu +5 more
openaire +1 more source