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
Book ChapterDOI
Negative Margin Matters: Understanding Margin in Few-Shot Classification
TL;DR: In this article, negative margin loss is introduced to metric learning based few-shot learning methods, which significantly outperforms regular softmax loss, and achieves state-of-the-art accuracy.
Proceedings ArticleDOI
Transductive Episodic-Wise Adaptive Metric for Few-Shot Learning
TL;DR: TEAM as mentioned in this paper integrates the meta-learning paradigm with both deep metric learning and transductive inference to learn a generalizable classifier with the capability of adapting to specific tasks with severely limited data.
Posted Content
Finding Task-Relevant Features for Few-Shot Learning by Category Traversal
TL;DR: In this paper, a category traversal module is proposed to identify task-relevant features based on both intra-class commonality and inter-class uniqueness in the feature space, which can be inserted as a plug-and-play module into most metric-learning based few-shot learners.
Journal ArticleDOI
RLBench: The Robot Learning Benchmark & Learning Environment
TL;DR: RLBench as discussed by the authors is a large-scale few-shot benchmark for robot learning with hundreds of hand-designed tasks, ranging from simple target reaching and door opening to longer multi-stage tasks such as opening an oven and placing a tray in it.
Journal ArticleDOI
Multi-Scale Metric Learning for Few-Shot Learning
TL;DR: A novel few-shot learning method named multi-scale metric learning (MSML) is proposed to extract multi- Scale features and learn the multi- scale relations between samples for the classification of few- shot learning.
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.