Semantic-Based Few-Shot Learning by Interactive Psychometric Testing

TL;DR

This paper introduces a semantic-based few-shot learning approach that leverages interactive psychometric testing to better capture complex semantic relationships, improving classification in challenging scenarios.

Contribution

It proposes a novel method using psychometric testing to incorporate semantic relationships into few-shot learning, addressing limitations of label-based supervision.

Findings

Outperforms baseline methods on CIFAR-100 in semantic classification tasks.

Effectively captures complex semantic relationships between classes.

Enhances few-shot learning in scenarios with high-level concept matching.

Abstract

Few-shot classification tasks aim to classify images in query sets based on only a few labeled examples in support sets. Most studies usually assume that each image in a task has a single and unique class association. Under these assumptions, these algorithms may not be able to identify the proper class assignment when there is no exact matching between support and query classes. For example, given a few images of lions, bikes, and apples to classify a tiger. However, in a more general setting, we could consider the higher-level concept, the large carnivores, to match the tiger to the lion for semantic classification. Existing studies rarely considered this situation due to the incompatibility of label-based supervision with complex conception relationships. In this work, we advance the few-shot learning towards this more challenging scenario, the semantic-based few-shot learning, and propose a method to address the paradigm by capturing the inner semantic relationships using interactive psychometric learning. The experiment results on the CIFAR-100 dataset show the superiority of our method for the semantic-based few-shot learning compared to the baseline.