Lightweight image classifier for CIFAR-10
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Image classification is one of the fundamental applications of computer vision. It enables a system to identify an object in an image. Recently, image classification applications have broadened their scope from computer applications to edge devices. The convolutional neural network (CNN) is the main class of deep learning neural networks that are widely used in computer tasks, and it delivers high accuracy. However, CNN algorithms use a large number of parameters and incur high computational costs, which hinder their implementation in edge hardware devices. To address this issue, this paper proposes a lightweight image classifier that provides good accuracy while using fewer parameters. The proposed image classifier diverts the input into three paths and utilizes different scales of receptive fields to extract more feature maps while using fewer parameters at the time of training. This results in the development of a model of small size. This model is tested on the CIFAR-10 dataset and achieves an accuracy of 90% using .26M parameters. This is better than the state-of-the-art models, and it can be implemented on edge devices.
Abstract
Image classification is one of the fundamental applications of computer vision. It enables a system to identify an object in an image. Recently, image classification applications have broadened their scope from computer applications to edge devices. The convolutional neural network (CNN) is the main class of deep learning neural networks that are widely used in computer tasks, and it delivers high accuracy. However, CNN algorithms use a large number of parameters and incur high computational costs, which hinder their implementation in edge hardware devices. To address this issue, this paper proposes a lightweight image classifier that provides good accuracy while using fewer parameters. The proposed image classifier diverts the input into three paths and utilizes different scales of receptive fields to extract more feature maps while using fewer parameters at the time of training. This results in the development of a model of small size. This model is tested on the CIFAR-10 dataset and achieves an accuracy of 90% using .26M parameters. This is better than the state-of-the-art models, and it can be implemented on edge devices.
참고문헌 (12)
- F. Sultana, "Advancements in image classification using convolutional neural network", Proc. of IEEE 2018 Fourth Int. Conf. on Res. Comput. Intell. Commun. Netw, 122(129), pp.122~129 (2018)
- R. Hecht-Nielsen, "Theory of the backpropagation neural network", Proc. of IEEE IJCNN, pp.593~605 (1989)
- D. H. Hubel, "Receptive fields and functional architecture of monkey striate cortex", J. Physiol., 195(1), pp.215~243 (1968)
- K. Fukushima, "Neocognitron : A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position", Biol. Cybern., 36(4), pp.193~202 (1980)
- Y. Lecun, "Gradientbased learning applied to document recognition", Proc. of IEEE, 86(11), pp.2278~2324 (1998)
- J. Deng, "Imagenet : A large-scale hierarchical image database", Proc. of IEEE Conf. on Comput. Vis. Pattern Recognit., pp.248~255 (2009)
- A. G. Howard, "Mobilenets : Efficient convolutional neural networks for mobile vision applications", Proc. Conf. on Comput. Vis. Pattern Recognit., pp.1704.04861~1704.04861 (2017)
- X. Zhang, "ShuffleNet: An extremely efficient convolutional neural network for mobile devices", Proc. of IEEE Conf. on Comput. Vis. Pattern Recognit, pp.6848~6856 (2018)
- I. N. Junejo, "Depthwise separable convolutional neural networks for pedestrian attribute recognition", SN Comput. Sci., 2(2), pp.1~11 (2021)
- G. Huang, "Densely connected convolutional networks", Proc. of IEEE Conf. on Comput. Vis. Pattern Recognit., pp.4700~4708 (2017)
- W. Sun, "Lightweight image classifier using dilated and depthwise separable convolutions", J. Cloud Comp., 9(1), pp.1~12 (2020)