Feature Map Reduction in CNN for Handwritten Digit Recognition

Chakraborty, Sinjan; Paul, Sayantan; Sarkar, Ram; Nasipuri, Mita

doi:10.1007/978-981-13-1280-9_14

Cited by 12 publications

(7 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…OctConv [4] is proposed to process low-frequency and high-frequency features separately to reduce the number of computations and parameters. In [1], authors randomly drop a certain amount of feature maps, hoping to reduce redundancy, whereas, in [6], authors predict a majority of the weights using a small subset. In contrast, we approach this redundancy, observing it as the correlation between convolutional filters and controlling it.…”

Section: Related Workmentioning

confidence: 99%

“…Therefore, we replace the conventional convolutional layers of such networks for classification, with LinearConv layers. Here, PyTorch framework [20] is used for implementation 1 and the network architectures considered are presented in Table 1. Base configuration is a simple baseline model of a few convolutional layers.…”

Section: Implementation Detailsmentioning

confidence: 99%

“…In such a resourceful setting, research community has put forth deep learning models with exceptional performance at the cost of heavy computation and memory usage. Recent studies suggest-although the automated feature learning process captures more meaningful and high-level featuresthat the accuracy gain comes with a considerable redundancy in learned features [6,1,26]. Such an inefficiency of the process hinders the deployment of deep learning models in resource-constrained environments.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Exploiting the Redundancy in Convolutional Filters for Parameter Reduction

Kahatapitiya¹,

Rodrigo²

2019

Preprint

View full text Add to dashboard Cite

Convolutional Neural Networks (CNNs) show state-ofthe-art performance in computer vision tasks. However, convolutional layers of CNNs are known to learn redundant features, still not being efficient in memory requirement. In this work, we explore the redundancy of learned features in the form of correlation between convolutional filters, and propose a novel layer to reproduce it efficiently. The proposed "LinearConv" layer generates a portion of convolutional filters as a learnable linear combination of the rest of the filters and introduces a correlation-based regularization to achieve flexibility and control over the correlation between filters, and the number of parameters, in turn. This is developed as a plug-in layer to conveniently replace a conventional convolutional layer without any modification required in the network architecture. Our experiments verify that the LinearConv-based models are able to achieve a performance on-par with counterparts with up to 50% of parameter reduction, and having same computational requirement in run time.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Implementation Detailsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Exploiting the Redundancy in Convolutional Filters for Parameter Reduction

Kahatapitiya¹,

Rodrigo²

2019

Preprint

View full text Add to dashboard Cite

show abstract

“…A constructed deep learning model can reflect the correlation between input and output data by extracting the features of input data, iteratively training the model, and dynamically adjusting the model parameters. As a class of neural networks in deep learning, the convolutional neural network (CNN) is widely used in medical image analysis [23], gesture recognition [24], emotional frame recognition [25], air quality prediction [26], and other fields, because it can extract features within a specific space [27]. Zheng et al [28] used a residual neural network framework to simulate the time, period, and trend features of crowd flow and predict regional traffic flow.…”

Section: Introductionmentioning

confidence: 99%

Site Selection Improvement of Retailers Based on Spatial Competition Strategy and a Double-Channel Convolutional Neural Network

Ouyang

Fan

Wang

et al. 2020

IJGI

View full text Add to dashboard Cite

The issue of site selection has become a critical challenge in the development of the retail industry with the growth of the Chinese economy and the improvement in the level of household consumption. Previous studies have considered the area of stores as the main factor of retail competition; however, the actual business performance of different stores in these studies was ignored. In addition, few studies have considered the differences in the spatial distribution of the factors of site selection. In this study, we discuss the improvement of site selection of small retail shops. A spatial competition index model was proposed as one of the features in estimating region market potential, and a market demand regression model of a double-channel convolutional neural network (CNN) was constructed based on the spatial correlation range of features. The study area was Guiyang, China. The experiments were based on the monthly sales data of fast-moving consumer goods retail stores in Guiyang. On the basis of the estimated results of the model, 18 sites with high potential for market demand were recommended. The performance of the proposed model was the best among well-known regression methods. Moreover, in comparison with a single-channel CNN, the proposed model decreased the root mean square error by 22.61%. Evaluation results showed that the proposed method could provide effective decision support for the issue of retail site selection.

show abstract

“…Moreover, architectures like CNN are computationally expensive and lead to wastage of resources when used with less complex research problems [40]. Here, we attempt to reduce the overall classification time by reducing the feature space used to train the model to get an optimal model to classify handwritten digits.…”

Section: Introductionmentioning

confidence: 99%

An efficient and improved scheme for handwritten digit recognition based on convolutional neural network

et al. 2019

View full text Add to dashboard Cite

Character recognition from handwritten images has received greater attention in research community of pattern recognition due to vast applications and ambiguity in learning methods. Primarily, two steps including character recognition and feature extraction are required based on some classification algorithm for handwritten digit recognition. Former schemes exhibit lack of high accuracy and low computational speed for handwritten digit recognition process. The aim of the proposed endeavor was to make the path toward digitalization clearer by providing high accuracy and faster computational for recognizing the handwritten digits. The present research employed convolutional neural network as classifier, MNIST as dataset with suitable parameters for training and testing and DL4J framework for hand written digit recognition. The aforementioned system successfully imparts accuracy up to 99.21% which is higher than formerly proposed schemes. In addition, the proposed system reduces computational time significantly for training and testing due to which algorithm becomes efficient.

show abstract

Feature Map Reduction in CNN for Handwritten Digit Recognition

Cited by 12 publications

References 9 publications

Exploiting the Redundancy in Convolutional Filters for Parameter Reduction

Exploiting the Redundancy in Convolutional Filters for Parameter Reduction

Site Selection Improvement of Retailers Based on Spatial Competition Strategy and a Double-Channel Convolutional Neural Network

An efficient and improved scheme for handwritten digit recognition based on convolutional neural network

Contact Info

Product

Resources

About