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
Hypernetworks in Meta-Reinforcement Learning
TL;DR: It is shown that hypernetwork initialization is also a critical factor in meta-RL, and that naive initializations yield poor performance, and a novel hyper network initialization scheme is proposed that matches or exceeds the performance of a state-of-the-art approach proposed for supervised settings.
Proceedings Article
Towards better understanding and better generalization of few-shot classification in histology images with contrastive learning
TL;DR: This work facilitates the study of few-shot learning in histology images by setting up three cross-domain tasks that simulate real clinics problems, and shows the superiority of CL over supervised learning in terms of generalization for such data.
Hybrid Sequence Encoder for Text Based Video Retrieval.
TL;DR: This report presents a hybrid sequential encoder which make use of the utilities of not only the multi-modal sources but also the feature extractors such as GRU, aggregated vectors, graph modeling, etc in this AVS task.
Journal ArticleDOI
Wave-SAN: Wavelet based Style Augmentation Network for Cross-Domain Few-Shot Learning
TL;DR: This paper studies the problem of CD-FSL by spanning the style distributions of the source dataset, and proposes a novel Style Augmentation (StyleAug) module and a Self-Supervised Learning (SSL) module to ensure the predictions of style-augmented images are semantically similar to the unchanged ones.
Journal ArticleDOI
Multi-instance attention network for few-shot learning
TL;DR: MIAN as discussed by the authors split the original image into patches, extending a new dimension in image data, namely, the patch dimension, which can benefit from multi-instance learning and achieve a good compromise between global and local features.
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.