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
SIM: an improved few-shot image classification model with multi-task learning
TL;DR: Wang et al. as discussed by the authors proposed an improved few-shot image classification model based on multi-task learning, which combines the self-supervised image representation learning task with the supervised image classification task, thus utilizing the complementarity of these two tasks.
Journal ArticleDOI
PFEMed: Few-shot medical image classification using prior guided feature enhancement
TL;DR: Li et al. as mentioned in this paper proposed PFEMed, a novel few-shot classification method for medical images, which employs a dual-encoder structure, that is, one encoder with fixed weights pre-trained on public image classification datasets and another encoder trained on the target medical dataset.
MonographDOI
Tutorial on Amortized Optimization
TL;DR: Amortized optimization as discussed by the authors uses learning to predict the solutions to problems in these settings, exploiting the shared structure between similar problem instances, and is capable of solving optimization problems many orders of magnitudes times faster than traditional optimization methods.
Journal ArticleDOI
Meta-Learning via Classifier(-free) Guidance
TL;DR: This work takes inspiration from recent advances in generative modeling and language-conditioned image synthesis to propose meta-learning techniques that use natural language guidance to achieve higher zero-shot performance compared to the state-of-the-art.
Journal ArticleDOI
Meta-Ensemble Parameter Learning
TL;DR: WeightFormer is introduced, a Transformer-based model that can predict student network weights layer by layer in a forward pass, according to the teacher model parameters, and can be straightforwardly extended to handle unseen teacher models compared with knowledge distillation and even exceeds average ensemble with small-scale tuning.
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.