DeepAI AI Chat
Log In Sign Up

Transductive Propagation Network for Few-shot Learning

by   Yanbin Liu, et al.
University of Oxford
University of Technology Sydney

Few-shot learning aims to build a learner that quickly generalizes to novel classes even when a limited number of labeled examples (so-called low-data problem) are available. Meta-learning is commonly deployed to mimic the test environment in a training phase for good generalization, where episodes (i.e., learning problems) are manually constructed from the training set. This framework gains a lot of attention to few-shot learning with impressive performance, though the low-data problem is not fully addressed. In this paper, we propose Transductive Propagation Network (TPN), a transductive method that classifies the entire test set at once to alleviate the low-data problem. Specifically, our proposed network explicitly learns an underlying manifold space that is appropriate to propagate labels from few-shot examples, where all parameters of feature embedding, manifold structure, and label propagation are estimated in an end-to-end way on episodes. We evaluate the proposed method on the commonly used miniImageNet and tieredImageNet benchmarks and achieve the state-of-the-art or promising results on these datasets.


Looking back to lower-level information in few-shot learning

Humans are capable of learning new concepts from small numbers of exampl...

MetaConcept: Learn to Abstract via Concept Graph for Weakly-Supervised Few-Shot Learning

Meta-learning has been proved to be an effective framework to address fe...

Incremental Few-Shot Learning with Attention Attractor Networks

Machine learning classifiers are often trained to recognize a set of pre...

Interval Bound Propagationx2013aided Fewx002dshot Learning

Few-shot learning aims to transfer the knowledge acquired from training ...

ReMP: Rectified Metric Propagation for Few-Shot Learning

Few-shot learning features the capability of generalizing from a few exa...

Constrained Few-Shot Learning: Human-Like Low Sample Complexity Learning and Non-Episodic Text Classification

Few-shot learning (FSL) is an emergent paradigm of learning that attempt...

Local Propagation for Few-Shot Learning

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