TY - JOUR
T1 - Consecutive multiscale feature learning-based image classification model
AU - Olimov, Bekhzod
AU - Subramanian, Barathi
AU - Ugli, Rakhmonov Akhrorjon Akhmadjon
AU - Kim, Jea Soo
AU - Kim, Jeonghong
N1 - Publisher Copyright:
© 2023, The Author(s).
PY - 2023/12
Y1 - 2023/12
N2 - Extracting useful features at multiple scales is a crucial task in computer vision. The emergence of deep-learning techniques and the advancements in convolutional neural networks (CNNs) have facilitated effective multiscale feature extraction that results in stable performance improvements in numerous real-life applications. However, currently available state-of-the-art methods primarily rely on a parallel multiscale feature extraction approach, and despite exhibiting competitive accuracy, the models lead to poor results in efficient computation and low generalization on small-scale images. Moreover, efficient and lightweight networks cannot appropriately learn useful features, and this causes underfitting when training with small-scale images or datasets with a limited number of samples. To address these problems, we propose a novel image classification system based on elaborate data preprocessing steps and a carefully designed CNN model architecture. Specifically, we present a consecutive multiscale feature-learning network (CMSFL-Net) that employs a consecutive feature-learning approach based on the usage of various feature maps with different receptive fields to achieve faster training/inference and higher accuracy. In the conducted experiments using six real-life image classification datasets, including small-scale, large-scale, and limited data, the CMSFL-Net exhibits an accuracy comparable with those of existing state-of-the-art efficient networks. Moreover, the proposed system outperforms them in terms of efficiency and speed and achieves the best results in accuracy-efficiency trade-off.
AB - Extracting useful features at multiple scales is a crucial task in computer vision. The emergence of deep-learning techniques and the advancements in convolutional neural networks (CNNs) have facilitated effective multiscale feature extraction that results in stable performance improvements in numerous real-life applications. However, currently available state-of-the-art methods primarily rely on a parallel multiscale feature extraction approach, and despite exhibiting competitive accuracy, the models lead to poor results in efficient computation and low generalization on small-scale images. Moreover, efficient and lightweight networks cannot appropriately learn useful features, and this causes underfitting when training with small-scale images or datasets with a limited number of samples. To address these problems, we propose a novel image classification system based on elaborate data preprocessing steps and a carefully designed CNN model architecture. Specifically, we present a consecutive multiscale feature-learning network (CMSFL-Net) that employs a consecutive feature-learning approach based on the usage of various feature maps with different receptive fields to achieve faster training/inference and higher accuracy. In the conducted experiments using six real-life image classification datasets, including small-scale, large-scale, and limited data, the CMSFL-Net exhibits an accuracy comparable with those of existing state-of-the-art efficient networks. Moreover, the proposed system outperforms them in terms of efficiency and speed and achieves the best results in accuracy-efficiency trade-off.
UR - http://www.scopus.com/inward/record.url?scp=85149490936&partnerID=8YFLogxK
U2 - 10.1038/s41598-023-30480-8
DO - 10.1038/s41598-023-30480-8
M3 - Article
C2 - 36869132
AN - SCOPUS:85149490936
SN - 2045-2322
VL - 13
JO - Scientific Reports
JF - Scientific Reports
IS - 1
M1 - 3595
ER -