Learning to Support: Exploiting Structure Information in Support Sets for One-Shot Learning

by   Jinchao Liu, et al.

Deep Learning shows very good performance when trained on large labeled data sets. The problem of training a deep net on a few or one sample per class requires a different learning approach which can generalize to unseen classes using only a few representatives of these classes. This problem has previously been approached by meta-learning. Here we propose a novel meta-learner which shows state-of-the-art performance on common benchmarks for one/few shot classification. Our model features three novel components: First is a feed-forward embedding that takes random class support samples (after a customary CNN embedding) and transfers them to a better class representation in terms of a classification problem. Second is a novel attention mechanism, inspired by competitive learning, which causes class representatives to compete with each other to become a temporary class prototype with respect to the query point. This mechanism allows switching between representatives depending on the position of the query point. Once a prototype is chosen for each class, the predicated label is computed using a simple attention mechanism over prototypes of all considered classes. The third feature is the ability of our meta-learner to incorporate deeper CNN embedding, enabling larger capacity. Finally, to ease the training procedure and reduce overfitting, we averages the top t models (evaluated on the validation) over the optimization trajectory. We show that this approach can be viewed as an approximation to an ensemble, which saves the factor of t in training and test times and the factor of of t in the storage of the final model.


page 1

page 2

page 3

page 4


Representation based and Attention augmented Meta learning

Deep learning based computer vision fails to work when labeled images ar...

Learning to Propagate for Graph Meta-Learning

Meta-learning extracts the common knowledge acquired from learning diffe...

Few-shot Learning with LSSVM Base Learner and Transductive Modules

The performance of meta-learning approaches for few-shot learning genera...

Prototype Propagation Networks (PPN) for Weakly-supervised Few-shot Learning on Category Graph

A variety of machine learning applications expect to achieve rapid learn...

CAD: Co-Adapting Discriminative Features for Improved Few-Shot Classification

Few-shot classification is a challenging problem that aims to learn a mo...

Elimination of Non-Novel Segments at Multi-Scale for Few-Shot Segmentation

Few-shot segmentation aims to devise a generalizing model that segments ...

Few-shot Learning with Global Relatedness Decoupled-Distillation

Despite the success that metric learning based approaches have achieved ...

Please sign up or login with your details

Forgot password? Click here to reset