Log In Sign Up

Rethinking Class Relations: Absolute-relative Few-shot Learning

by   Hongguang Zhang, et al.

The majority of existing few-shot learning describe image relations with 0,1 binary labels. However, such binary relations are insufficient to teach the network complicated real-world relations, due to the lack of decision smoothness. Furthermore, current few-shot learning models capture only the similarity via relation labels, but they are not exposed to class concepts associated with objects, which is likely detrimental to the classification performance due to underutilization of the available class labels. To paraphrase, while children learn the concept of tiger from a few of examples with ease, and while they learn from comparisons of tiger to other animals, they are also taught the actual concept names. Thus, we hypothesize that in fact both similarity and class concept learning must be occurring simultaneously. With these observations at hand, we study the fundamental problem of simplistic class modeling in current few-shot learning, we rethink the relations between class concepts, and propose a novel absolute-relative learning paradigm to fully take advantage of label information to refine the image representations and correct the relation understanding. Our proposed absolute-relative learning paradigm improves the performance of several the state-of-the-art models on publicly available datasets.


page 3

page 5


One-shot Learning with Absolute Generalization

One-shot learning is proposed to make a pretrained classifier workable o...

DPGN: Distribution Propagation Graph Network for Few-shot Learning

We extend this idea further to explicitly model the distribution-level r...

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

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

Attributes2Classname: A discriminative model for attribute-based unsupervised zero-shot learning

We propose a novel approach for unsupervised zero-shot learning (ZSL) of...

Improving Few-shot Learning with Weakly-supervised Object Localization

Few-shot learning often involves metric learning-based classifiers, whic...

Few-shot Learning with Multi-scale Self-supervision

Learning concepts from the limited number of datapoints is a challenging...

Function-words Enhanced Attention Networks for Few-Shot Inverse Relation Classification

The relation classification is to identify semantic relations between tw...