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
Journal ArticleDOI
Powering Finetuning in Few-Shot Learning: Domain-Agnostic Bias Reduction with Selected Sampling
TL;DR: This paper proposes Distribution Calibration Module (DCM) and Selected Sampling (SS) to reduce, and achieves state-of-the-art results on Meta-Dataset with consistent performance boosts over ten datasets from different domains.
Posted Content
Learning to Learn Kernels with Variational Random Features
TL;DR: This work introduces kernels with random Fourier features in the meta-learning framework to leverage their strong few-shot learning ability and proposes meta variational random features (MetaVRF) to learn adaptive kernels for the base-learner, which is developed in a latent variable model.
Proceedings ArticleDOI
Few-Shot Classification with Contrastive Learning
TL;DR: A novel Contrastive learning-based framework that seamlessly integrates contrastive learning into both stages to improve the performance of few-shot classification and achieves competitive results.
Posted Content
Few-shot Classification via Adaptive Attention
TL;DR: This work proposes a novel few-shot learning method via optimizing and fast adapting the query sample representation based on very few reference samples and generating soft attention to refine the representation such that the relevant features from the query and support samples can be extracted for a better few- shot classification.
Journal ArticleDOI
Transductive Decoupled Variational Inference for Few-Shot Classification
Ajay K. Singh,Hadi Jamali-Rad +1 more
TL;DR: This work proposes a novel variational inference network for few-shot classification (coined as TRIDENT) to decouple the representation of an image into semantic and label latent variables, and simultaneously infer them in an intertwined fash- ion.
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.