PARN: Position-Aware Relation Networks for Few-Shot Learning

by   Ziyang Wu, et al.

Few-shot learning presents a challenge that a classifier must quickly adapt to new classes that do not appear in the training set, given only a few labeled examples of each new class. This paper proposes a position-aware relation network (PARN) to learn a more flexible and robust metric ability for few-shot learning. Relation networks (RNs), a kind of architectures for relational reasoning, can acquire a deep metric ability for images by just being designed as a simple convolutional neural network (CNN) [23]. However, due to the inherent local connectivity of CNN, the CNN-based relation network (RN) can be sensitive to the spatial position relationship of semantic objects in two compared images. To address this problem, we introduce a deformable feature extractor (DFE) to extract more efficient features, and design a dual correlation attention mechanism (DCA) to deal with its inherent local connectivity. Successfully, our proposed approach extents the potential of RN to be position-aware of semantic objects by introducing only a small number of parameters. We evaluate our approach on two major benchmark datasets, i.e., Omniglot and Mini-Imagenet, and on both of the datasets our approach achieves state-of-the-art performance with the setting of using a shallow feature extraction network. It's worth noting that our 5-way 1-shot result on Omniglot even outperforms the previous 5-way 5-shot results.


page 6

page 7


Learning to Compare: Relation Network for Few-Shot Learning

We present a conceptually simple, flexible, and general framework for fe...

Learning to Compare Relation: Semantic Alignment for Few-Shot Learning

Few-shot learning is a fundamental and challenging problem since it requ...

Prototypical Networks for Few-shot Learning

We propose prototypical networks for the problem of few-shot classificat...

Few-Shot Learning with Embedded Class Models and Shot-Free Meta Training

We propose a method for learning embeddings for few-shot learning that i...

Ensemble Making Few-Shot Learning Stronger

Few-shot learning has been proposed and rapidly emerging as a viable mea...

Transductive Few-Shot Classification on the Oblique Manifold

Few-shot learning (FSL) attempts to learn with limited data. In this wor...

Learning a Universal Template for Few-shot Dataset Generalization

Few-shot dataset generalization is a challenging variant of the well-stu...

Please sign up or login with your details

Forgot password? Click here to reset