Iterative label cleaning for transductive and semi-supervised few-shot learning

by   Michalis Lazarou, et al.

Few-shot learning amounts to learning representations and acquiring knowledge such that novel tasks may be solved with both supervision and data being limited. Improved performance is possible by transductive inference, where the entire test set is available concurrently, and semi-supervised learning, where more unlabeled data is available. These problems are closely related because there is little or no adaptation of the representation in novel tasks. Focusing on these two settings, we introduce a new algorithm that leverages the manifold structure of the labeled and unlabeled data distribution to predict pseudo-labels, while balancing over classes and using the loss value distribution of a limited-capacity classifier to select the cleanest labels, iterately improving the quality of pseudo-labels. Our solution sets new state of the art on four benchmark datasets, namely miniImageNet, tieredImageNet, CUB and CIFAR-FS, while being robust over feature space pre-processing and the quantity of available data.



There are no comments yet.


page 1

page 2

page 3

page 4


Instance Credibility Inference for Few-Shot Learning

Few-shot learning (FSL) aims to recognize new objects with extremely lim...

A Strong Baseline for Semi-Supervised Incremental Few-Shot Learning

Few-shot learning (FSL) aims to learn models that generalize to novel cl...

Few-shot Learning via Dependency Maximization and Instance Discriminant Analysis

We study the few-shot learning (FSL) problem, where a model learns to re...

PTN: A Poisson Transfer Network for Semi-supervised Few-shot Learning

The predicament in semi-supervised few-shot learning (SSFSL) is to maxim...

Local Propagation for Few-Shot Learning

The challenge in few-shot learning is that available data is not enough ...

Motion2Vec: Semi-Supervised Representation Learning from Surgical Videos

Learning meaningful visual representations in an embedding space can fac...

How to trust unlabeled data? Instance Credibility Inference for Few-Shot Learning

Deep learning based models have excelled in many computer vision task an...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.