Insights into few shot learning approaches for image scene classification
Mohamed Soudy; Afify, Yasmine M.; Nagwa Badr;
Abstract
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.
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.
Other data
Title | Insights into few shot learning approaches for image scene classification | Authors | Mohamed Soudy; Afify, Yasmine M. ; Nagwa Badr | Keywords | Few shot learning, Scene classification, Sun397, Places, Reptile | Issue Date | 2021 | Journal | PeerJ Comput. Sci. | Volume | 7 | DOI | 10.7717/peerj-cs.666 |
Recommend this item
Similar Items from Core Recommender Database
Items in Ain Shams Scholar are protected by copyright, with all rights reserved, unless otherwise indicated.