Associative memory optimized method on deep neural networks for image classification

[Display omitted] •We apply associative memory to image classification and boost the neural network classifiers.•Experiments on four datasets demonstrate the rationality and effectiveness of our method.•We reveal the advantages of association memory to improve the intelligence of deep neural network...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Information sciences Jg. 533; S. 108 - 119
Hauptverfasser: Yang, Gang, Ding, Fei
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Inc 01.09.2020
Schlagworte:
Algorithm optimization
Associative memory
Classification
LSTM
Associative memory
LSTM
Algorithm optimization
Classification
ISSN:0020-0255, 1872-6291
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:[Display omitted] •We apply associative memory to image classification and boost the neural network classifiers.•Experiments on four datasets demonstrate the rationality and effectiveness of our method.•We reveal the advantages of association memory to improve the intelligence of deep neural networks. Deep neural networks have achieved excellent performance in the field of image classification. However, even to state-of-the-art deep neural networks, there are still many critical images that are difficult to be classified effectively. Enlightened by the brain function of associative memory, we propose a novel classification optimization method based on deep neural networks to improve image classifiers. Psychologists have studied associative memory for a long time. A popular theory is that ideas and memory are associated together in the mind through experience. By applying this theory to object recognition, our method focuses on using the association among different images of the same category to improve image classifiers based on deep neural networks. The association, which is memorized by the LSTM network in our method, could infer a sequence of associative images and form inner data augmentation effectively. Further, we introduce the LSTM network into an end-to-end deep learning framework to boost the performance of image classifiers. Experiments on four benchmark datasets reveal that our method produces a consistent improvement to the existing powerful classifiers. Moreover, as far as we know, our method achieves the best classification accuracies of 97.3%, 96.0%, and 89.1% on Flower102, Caltech101, and Caltech256 datasets, respectively.
ISSN:0020-0255
1872-6291
DOI:10.1016/j.ins.2020.05.038