Convolution with Logarithmic Filter Groups for Efficient Shallow CNN

Lee, Tae Kwan; Baddar, Wissam Alhaj; Kim, Seong Tae; Ro, Yong Man

doi:10.1007/978-3-319-73603-7_10

Cited by 13 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deformable convolution is able to only focus on what they are interested in, making the feature maps are more representative. Moreover, there exist a variety of awesome convolutions, such as Separable convolutions [24], [25], [26], [27], [28], group convolutions [11], [29], [30], [31] and multi-dimensional convolutions, which are discussed in Section 3 and Section 5.…”

Section: Brief Overview Of Cnnmentioning

confidence: 99%

A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects

Liu

Yang

et al. 2022

IEEE Trans. Neural Netw. Learning Syst.

2,080

544

View full text Add to dashboard Cite

Convolutional Neural Network (CNN) is one of the most significant networks in the deep learning field. Since CNN made impressive achievements in many areas, including but not limited to computer vision and natural language processing, it attracted much attention both of industry and academia in the past few years. The existing reviews mainly focus on the applications of CNN in different scenarios without considering CNN from a general perspective, and some novel ideas proposed recently are not covered. In this review, we aim to provide novel ideas and prospects in this fast-growing field as much as possible. Besides, not only two-dimensional convolution but also one-dimensional and multi-dimensional ones are involved. First, this review starts with a brief introduction to the history of CNN. Second, we provide an overview of CNN. Third, classic and advanced CNN models are introduced, especially those key points making them reach state-of-the-art results. Fourth, through experimental analysis, we draw some conclusions and provide several rules of thumb for function selection. Fifth, the applications of onedimensional, two-dimensional, and multi-dimensional convolution are covered. Finally, some open issues and promising directions for CNN are discussed to serve as guidelines for future work.

show abstract

Section: Brief Overview Of Cnnmentioning

confidence: 99%

A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects

Liu

Yang

et al. 2022

IEEE Trans. Neural Netw. Learning Syst.

2,080

544

View full text Add to dashboard Cite

show abstract

“…To further improve the segmentation accuracy, shuffle [ 11 ] and group [ 12 ] convolution were added to the segmentation architecture. By integrating the group convolution, segmentation features can be learned in a block way, where the filters with high correlation can be trained efficiently [ 13 ]. A shuffle operation was also added to overcome the issue of limited training variations, because only a small fraction of the input channel is utilized in standard group convolution.…”

Section: Introductionmentioning

confidence: 99%

Group and Shuffle Convolutional Neural Networks with Pyramid Pooling Module for Automated Pterygium Segmentation

Abdani

Zulkifley

2021

Diagnostics

View full text Add to dashboard Cite

Pterygium is an eye condition that is prevalent among workers that are frequently exposed to sunlight radiation. However, most of them are not aware of this condition, which motivates many volunteers to set up health awareness booths to give them free health screening. As a result, a screening tool that can be operated on various platforms is needed to support the automated pterygium assessment. One of the crucial functions of this assessment is to extract the infected regions, which directly correlates with the severity levels. Hence, Group-PPM-Net is proposed by integrating a spatial pyramid pooling module (PPM) and group convolution to the deep learning segmentation network. The system uses a standard mobile phone camera input, which is then fed to a modified encoder-decoder convolutional neural network, inspired by a Fully Convolutional Dense Network that consists of a total of 11 dense blocks. A PPM is integrated into the network because of its multi-scale capability, which is useful for multi-scale tissue extraction. The shape of the tissues remains relatively constant, but the size will differ according to the severity levels. Moreover, group and shuffle convolution modules are also integrated at the decoder side of Group-PPM-Net by placing them at the starting layer of each dense block. The addition of these modules allows better correlation among the filters in each group, while the shuffle process increases channel variation that the filters can learn from. The results show that the proposed method obtains mean accuracy, mean intersection over union, Hausdorff distance, and Jaccard index performances of 0.9330, 0.8640, 11.5474, and 0.7966, respectively.

show abstract

“…Compared to single SCNN, the architecture uses the combinations of CNN and SVM to achieve higher classification result. Lee et al [9] introduces logarithmic group convolution module with 1×1 and 3×3 convolutions to reduce the size of model in SCNN. In [10]- [12], the authors apply batch normalization (BN) technology [13] to SCNN to speed up training and improve accuracy.…”

Section: Introductionmentioning

confidence: 99%

Shallow Convolutional Neural Network for Image Recognition

Lei¹,

Liu²,

Jiang³

et al. 2019

IJCEE

View full text Add to dashboard Cite

Deep convolutional neural networks (DCNNs) have achieved state-of-the-art results for image recognition. However, these DCNNs with complex structure consist of many layers like convolutional layers, which require high time and computational complexity for training. Therefore, we propose a novel shallow convolutional neural network (SCNND) with dropout to address the problems of the DCNNs for image recognition. The SCNND with 4 layers can fast learning the features of the images, using dropout technology between two convolutional layers to improve recognition performance. Compared to the SCNNs, our SCNND includes 4 layers, with low time complexity and parameters. Experimental results show that our SCNND outperforms shallow CNN methods on Fashion-MNIST dataset.

show abstract

Convolution with Logarithmic Filter Groups for Efficient Shallow CNN

Cited by 13 publications

References 13 publications

A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects

A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects

Group and Shuffle Convolutional Neural Networks with Pyramid Pooling Module for Automated Pterygium Segmentation

Shallow Convolutional Neural Network for Image Recognition

Contact Info

Product

Resources

About