Dilated convolutions for image classification and object localization

Kudo, Yuta; Aoki, Yoshimitsu

doi:10.23919/mva.2017.7986898

Cited by 20 publications

(14 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We include the option to use dilated convolutional layers throughout the model to increase the receptive field of the model without increasing the parameter count. This approach has been effective in image classification tasks where a larger receptive field is desirable 24 .…”

Section: Deep Learning Model In Atacworkmentioning

confidence: 99%

AtacWorks: A deep convolutional neural network toolkit for epigenomics

Chiang

Yakovenko

et al. 2019

Preprint

View full text Add to dashboard Cite

We introduce AtacWorks ( https://github.com/clara-genomics/AtacWorks ), a method to denoise and identify accessible chromatin regions from low-coverage or low-quality ATAC-seq data. AtacWorks uses a deep neural network to learn a mapping between noisy ATAC-seq data and corresponding higher-coverage or higher-quality data. To demonstrate the utility of AtacWorks, we train a model on data from four blood cell types and show that this model accurately denoises and identifies peaks from low-coverage bulk sequencing of different individuals, cell types, and experimental conditions. Further, we show that the deep learning model can be generalized to denoise low-quality data, aggregate single-cell ATAC-seq profiles, and Tn5 insertion sites for transcription factor footprinting. Finally, we apply our deep learning approach to denoise single-cell ATAC-seq data from hematopoietic stem cells to identify differentially-accessible regulatory elements between rare lineage-primed cell subpopulations.

show abstract

Section: Deep Learning Model In Atacworkmentioning

confidence: 99%

AtacWorks: A deep convolutional neural network toolkit for epigenomics

Chiang

Yakovenko

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

“…Each discriminator includes convolution, instance normalization, and LeakyReLU activation functions. The coarse-scale discriminator uses dilated convolution [37] instead of ordinary convolution to reduce the information loss and make the receptive field exponentially grow [38]. The fine scale discriminator focuses on the local detail information and guides the generator to produce finer images.…”

Section: Methodsmentioning

confidence: 99%

High-Speed Railway Intruding Object Image Generating with Generative Adversarial Networks

Guo

Geng

Zhu

et al. 2019

Sensors

View full text Add to dashboard Cite

Foreign object intrusion is a great threat to high-speed railway safety operations. Accurate foreign object intrusion detection is particularly important. As a result of the lack of intruding foreign object samples during the operational period, artificially generated ones will greatly benefit the development of the detection methods. In this paper, we propose a novel method to generate railway intruding object images based on an improved conditional deep convolutional generative adversarial network (C-DCGAN). It consists of a generator and multi-scale discriminators. Loss function is also improved so as to generate samples with a high quality and authenticity. The generator is extracted in order to generate foreign object images from input semantic labels. We synthesize the generated objects to the railway scene. To make the generated objects more similar to real objects, on scale in different positions of a railway scene, a scale estimation algorithm based on the gauge constant is proposed. The experimental results on the railway intruding object dataset show that the proposed C-DCGAN model outperforms several state-of-the-art methods and achieves a higher quality (the pixel-wise accuracy, mean intersection-over-union (mIoU), and mean average precision (mAP) are 80.46%, 0.65, and 0.69, respectively) and diversity (the Fréchet-Inception Distance (FID) score is 26.87) of generated samples. The mIoU of the real-generated pedestrian pairs reaches 0.85, and indicates a higher scale of accuracy for the generated intruding objects in the railway scene.

show abstract

“…In CNN, increasing the diversity of the receptive field can ensure that the network extracts abundant contextual information. Dilated convolution operator is popularly attributed to the expansion capacity of the receptive field [23, 29]. Without losing the resolution or coverage, the dilated convolution can achieve the exponential expansion of the receptive field.…”

Section: Proposed Cnn‐based Mc2rnetmentioning

confidence: 99%