Deep Adaptive Wavelet Network

Rodriguez, Maria Ximena Bastidas; Gruson, Adrien; Polanía, Luisa F.; Fujieda, Shin; Ortiz, Franklin; Takayama, Kohei; Hachisuka, Toshiya

doi:10.1109/wacv45572.2020.9093580

Cited by 30 publications

(5 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lifting-based Adaptive Wavelet transform: Typically, the lifting transform (Sweldens 1998) consists of three fundamental steps (Sweldens and Schroder 1997;Claypoole et al 2003;Rodriguez et al 2020): split (lazy wavelet transform), predict, and update.…”

Section: Methodsmentioning

confidence: 99%

SEA-GWNN: Simple and Effective Adaptive Graph Wavelet Neural Network

Deb,

Rahman,

Rahman

2024

AAAI

View full text Add to dashboard Cite

The utilization of wavelet-based techniques in graph neural networks (GNNs) has gained considerable attention, particularly in the context of node classification. Although existing wavelet-based approaches have shown promise, they are constrained by their reliance on pre-defined wavelet filters, rendering them incapable of effectively adapting to signals that reside on graphs based on tasks at hand. Recent research endeavors address this issue through the introduction of a wavelet lifting transform. However, this technique necessitates the use of bipartite graphs, causing a transformation of the original graph structure into a bipartite configuration. This alteration of graph topology results in the generation of undesirable wavelet filters, thereby undermining the effectiveness of the method. In response to these challenges, we propose a novel simple and effective adaptive graph wavelet neural network (SEA-GWNN) class that employs the lifting scheme on arbitrary graph structures while upholding the original graph topology by leveraging multi-hop computation trees. A noteworthy aspect of the approach is the focus on local substructures represented as acyclic trees, wherein the lifting strategy is applied in a localized manner. This locally defined lifting scheme effectively combines high-pass and low-pass frequency information to enhance node representations. Furthermore, to reduce computing costs, we propose to decouple the higher- order lifting operators and induce them from the lower-order structures. Finally, we benchmark our model on several real- world datasets spanning four distinct categories, including citation networks, webpages, the film industry, and large-scale graphs and the experimental results showcase the efficacy of the proposed SEA-GWNN.

show abstract

Section: Methodsmentioning

confidence: 99%

SEA-GWNN: Simple and Effective Adaptive Graph Wavelet Neural Network

Deb,

Rahman,

Rahman

2024

AAAI

View full text Add to dashboard Cite

show abstract

“…The splitting operator is used to separate the input image into two parts, and the merging operator performs the inverse of the splitting operator. The splitting/merging operator in current methods [32]- [38], [40], [46] keep the same number of input and output coefficients.…”

Section: A Splitting/merging Operatormentioning

confidence: 99%

WINNet: Wavelet-inspired Invertible Network for Image Denoising

Huang,

Dragotti

2021

Preprint

View full text Add to dashboard Cite

Image denoising aims to restore a clean image from an observed noisy image. The model-based image denoising approaches can achieve good generalization ability over different noise levels and are with high interpretability. Learning-based approaches are able to achieve better results, but usually with weaker generalization ability and interpretability. In this paper, we propose a wavelet-inspired invertible network (WINNet) to combine the merits of the wavelet-based approaches and learningbased approaches. The proposed WINNet consists of K-scale of lifting inspired invertible neural networks (LINNs) and sparsitydriven denoising networks together with a noise estimation network. The network architecture of LINNs is inspired by the lifting scheme in wavelets. LINNs are used to learn a non-linear redundant transform with perfect reconstruction property to facilitate noise removal. The denoising network implements a sparse coding process for denoising. The noise estimation network estimates the noise level from the input image which will be used to adaptively adjust the soft-thresholds in LINNs. The forward transform of LINNs produce a redundant multi-scale representation for denoising. The denoised image is reconstructed using the inverse transform of LINNs with the denoised detail channels and the original coarse channel. The simulation results show that the proposed WINNet method is highly interpretable and has strong generalization ability to unseen noise levels. It also achieves competitive results in the non-blind/blind image denoising and in image deblurring.

show abstract

“…Traditional signal processing methodologies, such as multiresolution analysis utilizing wavelets, have been thoroughly investigated, allowing them to be more interpretable than CNNs. In fact, there have been several prior works, which have incorporated wavelet representations into CNNs [15]. Authors in [16] proposed Wavelet CNNs (WCNNs) and demonstrated how to generalize filtering and downsampling by reformulating convolution and pooling layers.…”

Section: Introductionmentioning

confidence: 99%

“…Authors in [18] used the Dual-Tree Complex Wavelet Transformation (DTCWT) in addition to WCNNs to solve the organ tissue image segmentation problem, whereas, by moving activation layers into wavelet space, authors in [19] employed a new concept of learning filters based on activations in the domain of wavelet. Authors in [15] describe the Deep Adaptive Wavelet Network (DAWN) architecture, which employs a combination of the lifting technique and CNNs to learn features via multi-resolution analysis. The DAWN algorithm is designed to obtain a wavelet representation of the input at each decomposition level.…”

Section: Introductionmentioning

confidence: 99%

An Enhanced Visual Object Tracking Approach based on Combined Features of Neural Networks, Wavelet Transforms, and Histogram of Oriented Gradients

Bourennane

Terki

Hamiane

et al. 2022

Eng. Technol. Appl. Sci. Res.

View full text Add to dashboard Cite

In this paper, a new Visual Object Tracking (VOT) approach is proposed to overcome the main problem the existing approaches encounter, i.e. the significant appearance changes which are mainly caused by heavy occlusion and illumination variation. The proposed approach is based on a combination of Deep Convolutional Neural Networks (DCNNs), Histogram of Oriented Gradient (HOG) features, and discrete wavelet packet transforms. The problem of illumination variation is solved by incorporating the coefficients of the image discrete wavelet packet transform instead of the image template to handle the case of images with high saturation in the input of the used CNN, whereas the inverse discrete wavelet packet transforms are used at the output for extracting the CNN features. By combining four learned correlation filters with the convolutional features, the target location is deduced using multichannel correlation maps at the CNN output. On the other side, the maximum value of the resulting maps from the correlation filters with convolutional features produced by the previously obtained HOG feature of the image template are calculated and are used as an updating parameter of the correlation filters extracted from CNN and from HOG. The major aim is to ensure long-term memory of the target appearance so that the target item may be recovered if tracking fails. In order to increase the performance of HOG, the coefficients of the discrete packet wavelet transform are employed instead of the image template. The obtained results demonstrate the superiority of the proposed approach.

show abstract

Deep Adaptive Wavelet Network

Cited by 30 publications

References 15 publications

SEA-GWNN: Simple and Effective Adaptive Graph Wavelet Neural Network

SEA-GWNN: Simple and Effective Adaptive Graph Wavelet Neural Network

WINNet: Wavelet-inspired Invertible Network for Image Denoising

An Enhanced Visual Object Tracking Approach based on Combined Features of Neural Networks, Wavelet Transforms, and Histogram of Oriented Gradients

Contact Info

Product

Resources

About