Open AccessPosted Content
Meta-Learning with Latent Embedding Optimization
Andrei Rusu,Dushyant Rao,Jakub Sygnowski,Oriol Vinyals,Razvan Pascanu,Simon Osindero,Raia Hadsell +6 more
Reads0
Chats0
TLDR
In this article, a data-dependent latent generative representation of model parameters is learned and a gradient-based meta-learning is performed in a low-dimensional latent space for few-shot learning.Abstract:
Gradient-based meta-learning techniques are both widely applicable and proficient at solving challenging few-shot learning and fast adaptation problems. However, they have practical difficulties when operating on high-dimensional parameter spaces in extreme low-data regimes. We show that it is possible to bypass these limitations by learning a data-dependent latent generative representation of model parameters, and performing gradient-based meta-learning in this low-dimensional latent space. The resulting approach, latent embedding optimization (LEO), decouples the gradient-based adaptation procedure from the underlying high-dimensional space of model parameters. Our evaluation shows that LEO can achieve state-of-the-art performance on the competitive miniImageNet and tieredImageNet few-shot classification tasks. Further analysis indicates LEO is able to capture uncertainty in the data, and can perform adaptation more effectively by optimizing in latent space.read more
Citations
More filters
Proceedings ArticleDOI
A Meta-Learning Framework for Predicting Power Digital Equipment Defect Texts via Hypergraph Modeling
Ling Luo,Xiaoyan Wang,Xiao Deng +2 more
TL;DR: In this paper , a meta-learning framework was proposed to solve the problem of small sample size and difficulty of scene migration, which is a way to acquire "learning to learn" and learn new tasks quickly based on the knowledge already acquired.
Journal ArticleDOI
Transductive Mutual Information Encoder Network for Few Shot Learning
Wei Huang,Caijun Ren +1 more
TL;DR: This paper proposes Transductive Mutual Information Encoder Network (TMIN) for few-shot learning problems, which typically trains a convolutional neural network with a mutual information maximization module in an unsupervised manner.
Journal ArticleDOI
Learning to Accelerate by the Methods of Step-size Planning
TL;DR: It is shown that for a convex problem, the methods surpass the convergence rate of Nesterov’s accelerated gradient, 1 − (cid:112) µL , where µ, L are the strongly convex factor of the loss function F and the Lipschitz constant of F ( cid:48) , which is the theoretical limit for the converge rate of first-order methods.
A Channel Coding Benchmark for Meta-Learning
TL;DR: This work proposes the channel coding problem as a benchmark for meta-learning, and uses the MetaCC benchmark to study several aspects of meta- learning, including the impact of task distribution breadth and shift, which can be controlled in the coding problem.
Journal ArticleDOI
Predicting the Generalization Ability of a Few-Shot Classifier
TL;DR: In this article, the authors investigate transfer-based few-shot learning solutions, and consider three settings: (i) supervised where they only have access to a few labeled samples, (ii) semi-supervised where they have access both a few labelled samples and a set of unlabeled samples and (iii) unsupervised when they only had access to unlabelled samples, and show that these simple measures can predict the generalization ability up to a certain confidence.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.