Wavelet Integrated CNNs for Noise-Robust Image Classification

Li, Qiufu; Shen, Linlin; Guo, Sheng; Lai, Zhihui

doi:10.1109/cvpr42600.2020.00727

Cited by 132 publications

(79 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Over the years, these basic model families produced several versions [74] and they have been extensively used by other researchers to develop modified and hybrid models [76] . Recent studies attempted to improve performance of the base models by proposing new layers and filters such as Sparse Shift Filter [77] , Asymmetric Convolution Block [78] , Adder Networks [79] , Virtual Pooling [80] , Discrete Wavelet Transform [81] , and HetConv [82] , etc. Some recent substantial models have been developed based on the base models, such as Res2Net [83] and Wide ResNet [84] using the ResNet model; while Log Dense Net [85] and Sparse Net [86] using the DenseNet model.…”

Section: Model Developmentmentioning

confidence: 99%

COVID-19 Detection Through Transfer Learning Using Multimodal Imaging Data

et al. 2020

View full text Add to dashboard Cite

Detecting COVID-19 early may help in devising an appropriate treatment plan and disease containment decisions. In this study, we demonstrate how transfer learning from deep learning models can be used to perform COVID-19 detection using images from three most commonly used medical imaging modes X-Ray, Ultrasound, and CT scan. The aim is to provide over-stressed medical professionals a second pair of eyes through intelligent deep learning image classification models. We identify a suitable Convolutional Neural Network (CNN) model through initial comparative study of several popular CNN models. We then optimize the selected VGG19 model for the image modalities to show how the models can be used for the highly scarce and challenging COVID-19 datasets. We highlight the challenges (including dataset size and quality) in utilizing current publicly available COVID-19 datasets for developing useful deep learning models and how it adversely impacts the trainability of complex models. We also propose an image pre-processing stage to create a trustworthy image dataset for developing and testing the deep learning models. The new approach is aimed to reduce unwanted noise from the images so that deep learning models can focus on detecting diseases with specific features from them. Our results indicate that Ultrasound images provide superior detection accuracy compared to X-Ray and CT scans. The experimental results highlight that with limited data, most of the deeper networks struggle to train well and provides less consistency over the three imaging modes we are using. The selected VGG19 model, which is then extensively tuned with appropriate parameters, performs in considerable levels of COVID-19 detection against pneumonia or normal for all three lung image modes with the precision of up to 86% for X-Ray, 100% for Ultrasound and 84% for CT scans.

show abstract

Section: Model Developmentmentioning

confidence: 99%

COVID-19 Detection Through Transfer Learning Using Multimodal Imaging Data

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The wavelet transform decomposes the image into a combination of low-frequency images and detail (high-frequency) images, which represent the different structures of the image, so it is easy to extract the structural information and detailed information of the original image. In recent years, wavelet transform has been introduced into deep learning networks [19], [27]- [31] and has achieved good results. In this paper, we mainly introduce the wavelet transform as a sampling operation method.…”

Section: ) Wavelet-based Deep-learning Approachmentioning

confidence: 99%

“…By averaging multiple components of the wavelet transform as downsampling output, Duan et al [30] effectively suppressed noise and obtained SAR image segmentation with good labeling consistency. Li et al [31] discussed the relationship between DWT and downsampling and achieved better image classifications by abandoning the high-frequency components of discrete wavelet transform and noise. The wavelet transform considers both spatial and frequency information, while the moire fringe overlaps with the original image, which covers a wide range in both spatial and frequency domains.…”

Section: ) Wavelet-based Deep-learning Approachmentioning

confidence: 99%

Efficient Attention Fusion Network in Wavelet Domain for Demoireing

et al. 2021

View full text Add to dashboard Cite

When taking pictures of electronic screens or objects with high-frequency textures, people often run across colorful rainbow patterns that are known as ''moire'', seriously affecting the image quality and subsequent processing. Current methods for removing moire patterns mostly extract multiscale information by downsampling pooling layers, which may inevitably cause information loss. To address this issue, this paper proposes a demoireing method in the wavelet domain. By employing both discrete wavelet transform (DWT) and inverse discrete wavelet transform (IDWT) instead of traditional downsampling and upsampling, this method can effectively increase the network receptive field without information loss. In addition, to further reconstruct more details of moire patterns, this paper proposes an efficient attention fusion module (EAFM). With a combination of efficient channel attention, spatial attention and local residual learning, this module can self-adaptively learn various weights of feature information at different levels and inspire the network to focus more on effective information such as moire details to improve learning and demoireing performance. Extensive experiments based on public datasets have shown that this suggested method can efficiently remove moire patterns and has a good quantitative and qualitative performance.INDEX TERMS Demoire, deep learning, wavelet transform, attention mechanism.

show abstract

“…Furthermore, various types of wavelet-like deep auto-encoders have been proposed to accelerate deep neural networks [21], as well as different image-based applications, including image classification and medical imaging [22]. Recently, wavelet integrated CNNs have been demonstrated effective for robust image classification [23].…”

Section: Wavelets In Neural Networkmentioning

confidence: 99%

Noise Homogenization via Multi-Channel Wavelet Filtering for High-Fidelity Sample Generation in Gans

Zeng

Zhang²

2021

2021 IEEE International Conference on Multimedia and Expo (ICME)

View full text Add to dashboard Cite

In a typical Generative Adversarial Network (GAN), a noise is sampled to generate fake samples via a series of convolutional operations after random initialization. However, current GANs merely rely on the pixel space to sample the noise, increasing the difficulty of approaching the target distribution. Fortunately, the long proven wavelet transformation is able to decompose multiple spectral information from the images. In this work, we propose a novel multi-channel wavelet-based filtering method for GANs, to cope with this problem. The proposed WaveletNet embeds a wavelet deconvolution layer in the generator to take advantage of the wavelet deconvolution. By learning a filter with multiple channels, or multiple convolutional filters, it can efficiently homogenize the sampled noise via an averaging operation, to generate high-fidelity samples. We conducted benchmark experiments on the Fashion-MNIST, KMNIST, and SVHN datasets through an open GAN benchmark tool. The results showed that WaveletGAN has excellent performance in generating high-fidelity samples.

show abstract

Wavelet Integrated CNNs for Noise-Robust Image Classification

Cited by 132 publications

References 23 publications

COVID-19 Detection Through Transfer Learning Using Multimodal Imaging Data

COVID-19 Detection Through Transfer Learning Using Multimodal Imaging Data

Efficient Attention Fusion Network in Wavelet Domain for Demoireing

Noise Homogenization via Multi-Channel Wavelet Filtering for High-Fidelity Sample Generation in Gans

Contact Info

Product

Resources

About