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
Posted Content
Unsupervised Partial Point Set Registration via Joint Shape Completion and Registration
Xiang Li,Lingjing Wang,Yi Fang +2 more
TL;DR: The proposed self-supervised method is pure unsupervised and does not need any ground truth supervision, and the point set registration process can benefit from the joint optimization process of latent codes, which are enforced to represent the information of full shape instead of partial ones.
Journal ArticleDOI
Global-Local Interplay in Semantic Alignment for Few-Shot Learning
TL;DR: Zhang et al. as discussed by the authors proposed a Global-Local Interplay Metric Learning (GLIML) framework to employ the interplay between global features and local features to guide semantic alignment.
Proceedings Article
Robust Meta-learning for Mixed Linear Regression with Small Batches
TL;DR: In this article, the authors proposed a spectral approach that is simultaneously robust against outliers and achieves a graceful statistical trade-off; the lack of large-data tasks can be compensated for with smaller tasks, which can now be as small as O(log k).
Journal ArticleDOI
Graph Complemented Latent Representation for Few-Shot Image Classification
TL;DR: Wang et al. as mentioned in this paper proposed a graph complemented latent representation (GCLR) network for few-shot image classification, which embeds the representation into a latent space, in which the latent codes are reconstructed using variational information to enrich the representation.
Proceedings ArticleDOI
What Makes for Effective Few-shot Point Cloud Classification?
TL;DR: A novel plug-and-play component called Cross-Instance Adaptation (CIA) module is proposed, to address the high intra-class variances and subtle inter-class differences issues, which can be easily inserted into current baselines with significant performance improvement.
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.