Gestalt-Guided Image Understanding for Few-Shot Learning

TL;DR

This paper introduces a novel few-shot learning method inspired by Gestalt psychology principles, which enhances feature extraction and estimation without retraining, leading to improved performance on image understanding tasks.

Contribution

It applies Gestalt psychology principles to few-shot learning, proposing a plug-and-play approach that improves feature extraction and estimation without retraining.

Findings

Significant performance improvements on few-shot learning benchmarks.

Effective feature extraction based on Gestalt principles.

No need for retraining or fine-tuning to achieve better results.

Abstract

Due to the scarcity of available data, deep learning does not perform well on few-shot learning tasks. However, human can quickly learn the feature of a new category from very few samples. Nevertheless, previous work has rarely considered how to mimic human cognitive behavior and apply it to few-shot learning. This paper introduces Gestalt psychology to few-shot learning and proposes Gestalt-Guided Image Understanding, a plug-and-play method called GGIU. Referring to the principle of totality and the law of closure in Gestalt psychology, we design Totality-Guided Image Understanding and Closure-Guided Image Understanding to extract image features. After that, a feature estimation module is used to estimate the accurate features of images. Extensive experiments demonstrate that our method can improve the performance of existing models effectively and flexibly without retraining or fine-tuning. Our code is released on https://github.com/skingorz/GGIU.