An multi-scale learning network with depthwise separable convolutions

Wang, Gaihua; Yuan, Guoliang; Li, Tao; Liu, Meng

doi:10.1186/s41074-018-0047-6

Cited by 13 publications

(14 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compares to ( 2) and ( 4), DSC shows lower trainable parameters than conventional CNN, which is formulized as [20], [24]. Based on (5), it is proven that DSC reduces the trainable parameter of the convolution layer.…”

Section: Depthwise Separable Convolutional Neural Networkmentioning

confidence: 92%

See 1 more Smart Citation

Dental caries classification using depthwise separable convolutional neural network for teledentistry system

et al. 2023

View full text Add to dashboard Cite

Caries may be halted or reversed in their progression by early detection, better hygiene habits, and coadministered drugs. The major clinical procedures for identifying dental caries are visual-tactile examination and dental radiography. However, due to their location, approximate caries exceedingly difficult to detect and affect the clinical assessment. Incorrect interpretations may also hinder the diagnostic procedure. Computational approaches and technology can be used to help dentists assess caries. Teledentistry has the ability to improve dental health care by providing access to dental care services from a remote location. Teledentistry helps identifying various stages of caries lesions using neural network and devices connected to the internet. This research develops an image classification for teledentistry systems using depthwise separable convolutional neural network. The trainable parameters reduction of depthwise separable convolution (DSC) successfully reduces the computational cost of conventional convolutional neural networks (CNN). As a result, the DSC model is reduced by 91.49% when compared to the traditional CNN model. Several DSC models improve conventional CNN accuracies in the training, validation, evaluation, and testing stages.

show abstract

Section: Depthwise Separable Convolutional Neural Networkmentioning

confidence: 92%

“…Spatial location of (ℎ 𝑙 , 𝑤 𝑙 ) used from bank filter of 𝑓and 𝑑 𝑙 is a receptive field in 𝑥 𝑙 . Therefore, the total trainable parameters of the feature extraction represent as Kernel formulized as [20]:…”

Section: Depthwise Separable Convolutional Neural Networkmentioning

confidence: 99%

Dental caries classification using depthwise separable convolutional neural network for teledentistry system

et al. 2023

View full text Add to dashboard Cite

show abstract

“…To decrease the computational cost caused by the cascading networks, depthwise separable convolution, linear bottlenecks and inverted residuals are adopted to reduce the number of model parameters while maintaining the accuracy [43]. By implementing all the above-introduced improvements and techniques, the general flowchart of our proposed detection framework is shown in Figure 15, and the corresponding pseudocodes are presented in Algorithms 2 and Algorithms 3.…”

Section: Inputmentioning

confidence: 99%

Deep Learning Approaches on Defect Detection in High Resolution Aerial Images of Insulators

Wen

Luo

Chen

et al. 2021

Sensors

View full text Add to dashboard Cite

By detecting the defect location in high-resolution insulator images collected by unmanned aerial vehicle (UAV) in various environments, the occurrence of power failure can be timely detected and the caused economic loss can be reduced. However, the accuracies of existing detection methods are greatly limited by the complex background interference and small target detection. To solve this problem, two deep learning methods based on Faster R-CNN (faster region-based convolutional neural network) are proposed in this paper, namely Exact R-CNN (exact region-based convolutional neural network) and CME-CNN (cascade the mask extraction and exact region-based convolutional neural network). Firstly, we proposed an Exact R-CNN based on a series of advanced techniques including FPN (feature pyramid network), cascade regression, and GIoU (generalized intersection over union). RoI Align (region of interest align) is introduced to replace RoI pooling (region of interest pooling) to address the misalignment problem, and the depthwise separable convolution and linear bottleneck are introduced to reduce the computational burden. Secondly, a new pipeline is innovatively proposed to improve the performance of insulator defect detection, namely CME-CNN. In our proposed CME-CNN, an insulator mask image is firstly generated to eliminate the complex background by using an encoder-decoder mask extraction network, and then the Exact R-CNN is used to detect the insulator defects. The experimental results show that our proposed method can effectively detect insulator defects, and its accuracy is better than the examined mainstream target detection algorithms.

show abstract

“…Depthwise separable convolution have found success in a variety of applications [19,20,21,22]. The work of Nguyen and Ray proposed an adaptive convolution block method that learns the upsampling algorithm [23].…”

Section: Depthwise Separable Convolutionsmentioning

confidence: 99%

DepthwiseGANs: Fast Training Generative Adversarial Networks for Realistic Image Synthesis

Ngxande¹,

Tapamo

Burke

2019

2019 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of So

View full text Add to dashboard Cite

Recent work has shown significant progress in the direction of synthetic data generation using Generative Adversarial Networks (GANs). GANs have been applied in many fields of computer vision including text-to-image conversion, domain transfer, super-resolution, and image-to-video applications. In computer vision, traditional GANs are based on deep convolutional neural networks. However, deep convolutional neural networks can require extensive computational resources because they are based on multiple operations performed by convolutional layers, which can consist of millions of trainable parameters. Training a GAN model can be difficult and it takes a significant amount of time to reach an equilibrium point. In this paper, we investigate the use of depthwise separable convolutions to reduce training time while maintaining data generation performance. Our results show that a DepthwiseGAN architecture can generate realistic images in shorter training periods when compared to a StarGan architecture, but that model capacity still plays a significant role in generative modelling. In addition, we show that depthwise separable convolutions perform best when only applied to the generator. For quality evaluation of generated images, we use the Fréchet Inception Distance (FID), which compares the similarity between the generated image distribution and that of the training dataset.

show abstract

An multi-scale learning network with depthwise separable convolutions

Cited by 13 publications

References 16 publications

Dental caries classification using depthwise separable convolutional neural network for teledentistry system

Dental caries classification using depthwise separable convolutional neural network for teledentistry system

Deep Learning Approaches on Defect Detection in High Resolution Aerial Images of Insulators

DepthwiseGANs: Fast Training Generative Adversarial Networks for Realistic Image Synthesis

Contact Info

Product

Resources

About