Deep Image Feature Learning with Fuzzy Rules

TL;DR

This paper introduces DIFL-FR, a novel interpretable and efficient deep image feature learning method using fuzzy rules, which avoids backpropagation and is suitable for various learning scenarios.

Contribution

It proposes a fuzzy rule-based deep learning approach that enhances interpretability and efficiency without relying on backpropagation.

Findings

Effective feature learning demonstrated on multiple datasets.

High learning efficiency due to forward-only propagation.

Versatile application in unsupervised, supervised, and semi-supervised settings.

Abstract

The methods of extracting image features are the key to many image processing tasks. At present, the most popular method is the deep neural network which can automatically extract robust features through end-to-end training instead of hand-crafted feature extraction. However, the deep neural network currently faces many challenges: 1) its effectiveness is heavily dependent on large datasets, so the computational complexity is very high; 2) it is usually regarded as a black box model with poor interpretability. To meet the above challenges, a more interpretable and scalable feature learning method, i.e., deep image feature learning with fuzzy rules (DIFL-FR), is proposed in the paper, which combines the rule-based fuzzy modeling technique and the deep stacked learning strategy. The method progressively learns image features through a layer-by-layer manner based on fuzzy rules, so the feature learning process can be better explained by the generated rules. More importantly, the learning process of the method is only based on forward propagation without back propagation and iterative learning, which results in the high learning efficiency. In addition, the method is under the settings of unsupervised learning and can be easily extended to scenes of supervised and semi-supervised learning. Extensive experiments are conducted on image datasets of different scales. The results obviously show the effectiveness of the proposed method.