Related papers: Wavelet Integrated CNNs for Noise-Robust Image Classification

Wavelet Integrated CNNs for Noise-Robust Image Classification

URL: http://arxiv.org/abs/2005.03337v2
Date: Tue, 14 Jul 2020 07:51:21 GMT
Title: Wavelet Integrated CNNs for Noise-Robust Image Classification
Authors: Qiufu Li, Linlin Shen, Sheng Guo, Zhihui Lai
Abstract summary: We enhance CNNs by replacing max-pooling, strided-convolution, and average-pooling with Discrete Wavelet Transform (DWT) WaveCNets, the wavelet integrated versions of VGG, ResNets, and DenseNet, achieve higher accuracy and better noise-robustness than their vanilla versions.
Score: 51.18193090255933
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Convolutional Neural Networks (CNNs) are generally prone to noise interruptions, i.e., small image noise can cause drastic changes in the output. To suppress the noise effect to the final predication, we enhance CNNs by replacing max-pooling, strided-convolution, and average-pooling with Discrete Wavelet Transform (DWT). We present general DWT and Inverse DWT (IDWT) layers applicable to various wavelets like Haar, Daubechies, and Cohen, etc., and design wavelet integrated CNNs (WaveCNets) using these layers for image classification. In WaveCNets, feature maps are decomposed into the low-frequency and high-frequency components during the down-sampling. The low-frequency component stores main information including the basic object structures, which is transmitted into the subsequent layers to extract robust high-level features. The high-frequency components, containing most of the data noise, are dropped during inference to improve the noise-robustness of the WaveCNets. Our experimental results on ImageNet and ImageNet-C (the noisy version of ImageNet) show that WaveCNets, the wavelet integrated versions of VGG, ResNets, and DenseNet, achieve higher accuracy and better noise-robustness than their vanilla versions.

Related papers

Multi-stage image denoising with the wavelet transform [125.2251438120701]
Deep convolutional neural networks (CNNs) are used for image denoising via automatically mining accurate structure information. We propose a multi-stage image denoising CNN with the wavelet transform (MWDCNN) via three stages, i.e., a dynamic convolutional block (DCB), two cascaded wavelet transform and enhancement blocks (WEBs) and residual block (RB)
arXiv Detail & Related papers (2022-09-26T03:28:23Z)
Wavelet-Attention CNN for Image Classification [0.0]
We propose a Wavelet-Attention convolutional neural network (WA-CNN) for image classification. WA-CNN decomposes the feature maps into low-frequency and high-frequency components for storing the structures of the basic objects. Our proposed WA-CNN achieves significant improvements in classification accuracy compared to other related networks.
arXiv Detail & Related papers (2022-01-23T14:00:33Z)
Exploring Inter-frequency Guidance of Image for Lightweight Gaussian Denoising [1.52292571922932]
We propose a novel network architecture denoted as IGNet, in order to refine the frequency bands from low to high in a progressive manner. With this design, more inter-frequency prior and information are utilized, thus the model size can be lightened while still perserves competitive results.
arXiv Detail & Related papers (2021-12-22T10:35:53Z)
Wavelet-Based Network For High Dynamic Range Imaging [64.66969585951207]
Existing methods, such as optical flow based and end-to-end deep learning based solutions, are error-prone either in detail restoration or ghosting artifacts removal. In this work, we propose a novel frequency-guided end-to-end deep neural network (FNet) to conduct HDR fusion in the frequency domain, and Wavelet Transform (DWT) is used to decompose inputs into different frequency bands. The low-frequency signals are used to avoid specific ghosting artifacts, while the high-frequency signals are used for preserving details.
arXiv Detail & Related papers (2021-08-03T12:26:33Z)
WaveCNet: Wavelet Integrated CNNs to Suppress Aliasing Effect for Noise-Robust Image Classification [41.94702591058716]
convolutional neural networks (CNNs) are prone to noise interruptions. We try to integrate CNNs with wavelet by replacing the common down-sampling with discrete wavelet transform (DWT) We have also tested the performance of WaveCNets on the noisy version of ImageNet, ImageNet-C and six adversarial attacks.
arXiv Detail & Related papers (2021-07-28T12:59:15Z)
Progressive Training of Multi-level Wavelet Residual Networks for Image Denoising [80.10533234415237]
This paper presents a multi-level wavelet residual network (MWRN) architecture as well as a progressive training scheme to improve image denoising performance. Experiments on both synthetic and real-world noisy images show that our PT-MWRN performs favorably against the state-of-the-art denoising methods.
arXiv Detail & Related papers (2020-10-23T14:14:00Z)
Wavelet Channel Attention Module with a Fusion Network for Single Image Deraining [46.62290347397139]
Single image deraining is a crucial problem because rain severely degenerates the visibility of images. We propose the new convolutional neural network (CNN) called the wavelet channel attention module with a fusion network.
arXiv Detail & Related papers (2020-07-17T18:06:13Z)
Flexible Image Denoising with Multi-layer Conditional Feature Modulation [56.018132592622706]
We present a novel flexible image enoising network (CFMNet) by equipping an U-Net backbone with conditional feature modulation (CFM) modules. In comparison to channel-wise shifting only in the first layer, CFMNet can make better use of noise level information by deploying multiple layers of CFM. Our CFMNet is effective in exploiting noise level information for flexible non-blind denoising, and performs favorably against the existing deep image denoising methods in terms of both quantitative metrics and visual quality.
arXiv Detail & Related papers (2020-06-24T06:00:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.