Open AccessInsights into few shot learning approaches for image scene classification
Author(s) -
Mohamed Soudy,
Yasmine M. Afify,
Nagwa L. Badr
Publication year - 2021
Publication title -
peerj. computer science
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.806
H-Index - 24
ISSN - 2376-5992
DOI - 10.7717/peerj-cs.666
Subject(s) - computer science , artificial intelligence , benchmark (surveying) , contextual image classification , machine learning , task (project management) , trace (psycholinguistics) , image (mathematics) , set (abstract data type) , pattern recognition (psychology) , computer vision , linguistics , philosophy , management , geodesy , economics , programming language , geography
Image understanding and scene classification are keystone tasks in computer vision. The development of technologies and profusion of existing datasets open a wide room for improvement in the image classification and recognition research area. Notwithstanding the optimal performance of exiting machine learning models in image understanding and scene classification, there are still obstacles to overcome. All models are data-dependent that can only classify samples close to the training set. Moreover, these models require large data for training and learning. The first problem is solved by few-shot learning, which achieves optimal performance in object detection and classification but with a lack of eligible attention in the scene classification task. Motivated by these findings, in this paper, we introduce two models for few-shot learning in scene classification. In order to trace the behavior of those models, we also introduce two datasets (MiniSun; MiniPlaces) for image scene classification. Experimental results show that the proposed models outperform the benchmark approaches in respect of classification accuracy.