Universidad Nacional de Colombia（哥伦比亚国立大学）；The University of Tokyo（东京大学）；McGill University（麦吉尔大学）；Target Corporation（塔吉特公司）；Digital Frontier Inc.（数字前沿公司）
Maria Ximena Bastidas Rodriguez, Adrien Gruson, Luisa F. Polania, Shin Fujieda, Flavio Prieto Ortiz, Kohei Takayama, Toshiya Hachisuka
Even though convolutional neural networks have become the method of choice in many fields of computer vision, they still lack interpretability and are usually designed manually in a cumbersome trial-and-error process. This paper aims at overcoming those limitations by proposing a deep neural network, which is designed in a systematic fashion and is interpretable, by integrating multiresolution analysis at the core of the deep neural network design. By using the lifting scheme, it is possible to generate a wavelet representation and design a network capable of learning wavelet coefficients in an end-to-end form. Compared to state-of-the-art architectures, the proposed model requires less hyper-parameter tuning and achieves competitive accuracy in image classification tasks
The rise of machine learning in image processing has created a gap between trainable data-driven and classical model-driven approaches: While learning-based models often show superior performance, classical ones are often more transparent. To reduce this gap, we introduce a generic wavelet shrinkage function for denoising which is adaptive to both the wavelet scales as well as the noise standard deviation. It is inferred from trained results of a tightly parametrised function which is inherited from nonlinear diffusion. Our proposed shrinkage function is smooth and compact while only using two…
Review of wavelet-based unsupervised texture segmentation, advantage of adaptive wavelets
Image Processing Center, Beihang University（北京航空航天大学图像处理中心）；Centre pour les Mathématiques et Leurs Applications, Ecole Normale Supérieure of Paris Saclay（巴黎萨克雷高等师范学院数学及其应用中心）；Department of Mathematics and Statistics, San Diego State University（圣地亚哥州立大学数学与统计系）
In this paper, we propose two contributions to neural network based denoising. First, we propose applying separate convolutional layers to each sub-band of discrete wavelet transform (DWT) as opposed to the common usage of DWT which concatenates all sub-bands and applies a single convolution layer. We show that our approach to using DWT in neural networks improves the accuracy notably, due to keeping the sub-band order uncorrupted prior to inverse DWT. Our second contribution is a denoising loss based on top k-percent of errors in frequency domain. A neural network trained with this loss, adap…
In this paper we propose a method of corner detection for obtaining features which is required to track and recognize objects within a noisy image. Corner detection of noisy images is a challenging task in image processing. Natural images often get corrupted by noise during acquisition and transmission. Though Corner detection of these noisy images does not provide desired results, hence de-noising is required. Adaptive wavelet thresholding approach is applied for the same.
RVS College of Engineering and Technology（RVS工程技术学院）
In recent years, many research achievements are made in the medical image fusion field. Fusion is basically extraction of best of inputs and conveying it to the output. Medical Image fusion means that several of various modality image information is comprehended together to form one image to express its information. The aim of image fusion is to integrate complementary and redundant information. In this paper, a multimodal image fusion algorithm based on the dual-tree complex wavelet transform (DT-CWT) and adaptive particle swarm optimization (APSO) is proposed. Fusion is achieved through the …
In this paper a comparative study between Moravec and Harris Corner Detection has been done for obtaining features required to track and recognize objects within a noisy image. Corner detection of noisy images is a challenging task in image processing. Natural images often get corrupted by noise during acquisition and transmission. As Corner detection of these noisy images does not provide desired results, hence de-noising is required. Adaptive wavelet thresholding approach is applied for the same.
Despite the remarkable success of deep learning in pattern recognition, deep network models face the problem of training a large number of parameters. In this paper, we propose and evaluate a novel multi-path wavelet neural network architecture for image classification with far less number of trainable parameters. The model architecture consists of a multi-path layout with several levels of wavelet decompositions performed in parallel followed by fully connected layers. These decomposition operations comprise wavelet neurons with learnable parameters, which are updated during the training phas…
The GHM multi-level discrete wavelet transform is proposed as preprocessing for image super resolution with convolutional neural networks. Previous works perform analysis with the Haar wavelet only. In this work, 37 single-level wavelets are experimentally analyzed from Haar, Daubechies, Biorthogonal, Reverse Biorthogonal, Coiflets, and Symlets wavelet families. All single-level wavelets report similar results indicating that the convolutional neural network is invariant to choice of wavelet in a single-level filter approach. However, the GHM multi-level wavelet achieves higher quality reconst…
Cardiovascular system study using ECG signals have evolved tremendously in the domain of electronics and signal processing. However, there are certain floating challenges unresolved in the analysis and detection of abnormal performances of cardiovascular system. As the medical field is moving towards more automated and intelligent systems, wrong detection or wrong interpretations of ECG waveform of abnormal conditions can be quite fatal. Since the PQRST signals vary their positions randomly, the process of locating, identifying and classifying each feature can be cumbersome and it is prone to …
Rochester Institute of Technology（罗切斯特理工学院）；Verisk AI, Verisk Analytics（Verisk分析公司Verisk人工智能部门）
Variational Autoencoders (VAE) are probabilistic deep generative models underpinned by elegant theory, stable training processes, and meaningful manifold representations. However, they produce blurry images due to a lack of explicit emphasis over high-frequency textural details of the images, and the difficulty to directly model the complex joint probability distribution over the high-dimensional image space. In this work, we approach these two challenges with a novel wavelet space VAE that uses the decoder to model the images in the wavelet coefficient space. This enables the VAE to emphasize…
Unsupervised deep learning has recently demonstrated the promise of producing high-quality samples. While it has tremendous potential to promote the image colorization task, the performance is limited owing to the high-dimension of data manifold and model capability. This study presents a novel scheme that exploits the score-based generative model in wavelet domain to address the issues. By taking advantage of the multi-scale and multi-channel representation via wavelet transform, the proposed model learns the richer priors from stacked coarse and detailed wavelet coefficient components jointl…
Cloud detection is a specialized application of image recognition and object detection using remotely sensed data. The task presents a number of challenges, including analyzing images obtained in visible, infrared and multi-spectral frequencies, usually without ground truth data for comparison. Moreover, machine learning and deep learning (MLDL) algorithms applied to this task are required to be computationally efficient, as they are typically deployed in low-power devices and called to operate in real-time. This paper explains Wavelet Transform (WT) theory, comparing it to more widely used im…
We introduce a two-layer wavelet scattering network, for object classification. This scattering transform computes a spatial wavelet transform on the first layer and a new joint wavelet transform along spatial, angular and scale variables in the second layer. Numerical experiments demonstrate that this two layer convolution network, which involves no learning and no max pooling, performs efficiently on complex image data sets such as CalTech, with structural objects variability and clutter. It opens the possibility to simplify deep neural network learning by initializing the first layers with …
Shanghai Jiao Tong University（上海交通大学）；École Polytechnique Fédérale de Lausanne (EPFL)（洛桑联邦理工学院）
Pooling and unpooling are two essential operations in constructing hierarchical spherical convolutional neural networks (HS-CNNs) for comprehensive feature learning in the spherical domain. Most existing models employ downsampling-based pooling, which will inevitably incur information loss and cannot adapt to different spherical signals and tasks. Besides, the preserved information after pooling cannot be well restored by the subsequent unpooling to characterize the desirable features for a task. In this paper, we propose a novel framework of HS-CNNs with a lifting structure to learn adaptive …
Indian Institute of Technology Madras (IITM)（印度理工学院马德拉斯分校）；Healthcare Technology Innovation Centre (HTIC), IITM（印度理工学院马德拉斯分校医疗技术创新中心）
Several variants of Convolutional Neural Networks (CNN) have been developed for Magnetic Resonance (MR) image reconstruction. Among them, U-Net has shown to be the baseline architecture for MR image reconstruction. However, sub-sampling is performed by its pooling layers, causing information loss which in turn leads to blur and missing fine details in the reconstructed image. We propose a modification to the U-Net architecture to recover fine structures. The proposed network is a wavelet packet transform based encoder-decoder CNN with residual learning called CNN. The proposed WCNN has discret…
ARFC-WAHNet: Adaptive Receptive Field Convolution and Wavelet-Attentive Hierarchical Network for Infrared Small Target Detection
School of Information and Communication Engineering（信息与通信工程学院）；Laboratory of Imaging Detection and Intelligent Perception（成像检测与智能感知实验室）；University of Electronic Science and Technology of China（电子科学与技术大学）
In deep networks, the lost data details significantly degrade the performances of image segmentation. In this paper, we propose to apply Discrete Wavelet Transform (DWT) to extract the data details during feature map down-sampling, and adopt Inverse DWT (IDWT) with the extracted details during the up-sampling to recover the details. We firstly transform DWT/IDWT as general network layers, which are applicable to 1D/2D/3D data and various wavelets like Haar, Cohen, and Daubechies, etc. Then, we design wavelet integrated deep networks for image segmentation (WaveSNets) based on various architect…
Jiangsu Key Lab of Spectral Imaging & Intelligence Sense, Nanjing University of Science and Technology（南京理工大学江苏省光谱成像与智能感知重点实验室）；Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education, Nanjing University of Science and Technology（南京理工大学高维信息智能感知与系统教育部重点实验室）
Photon counting 3D imaging allows to obtain 3D images with single-photon sensitivity and sub-ns temporal resolution. However, it is challenging to scale to high spatial resolution. In this work, we demonstrate a photon counting 3D imaging technique with short-pulsed structured illumination and a single-pixel photon counting detector. The proposed multi-resolution photon counting 3D imaging technique acquires a high-resolution 3D image from a coarse image and edges at successfully finer resolution sampled by Hadamard multiplexing along the wavelet trees. The detected power is significantly incr…
Sichuan University（四川大学）；UC San Diego（加利福尼亚大学圣地亚哥分校）
JPEG is one of the widely used lossy compression methods. JPEG-compressed images usually suffer from compression artifacts including blocking and blurring, especially at low bit-rates. Soft decoding is an effective solution to improve the quality of compressed images without changing codec or introducing extra coding bits. Inspired by the excellent performance of the deep convolutional neural networks (CNNs) on both low-level and high-level computer vision problems, we develop a dual pixel-wavelet domain deep CNNs-based soft decoding network for JPEG-compressed images, namely DPW-SDNet. The pi…
Adaptive Wavelet Filters as Practical Texture Feature Amplifiers for Parkinson's Disease Screening in OCT
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Department of Computer Science and Engineering, Southern University of Science and Technology（南方科技大学计算机科学与工程系）；State Key Laboratory of Ophthalmology, Optometry and Vision Science, Wenzhou Medical University（温州医科大学眼视光学与视觉科学国家重点实验室）；Coventry University（考文垂大学）；School of Computer Science, University of Nottingham Ningbo China（宁波诺丁汉大学计算机学院）；School of Ophthalmology and Optometry, Wenzhou Medical University（温州医科大学眼视光学院）；Department of Electronic and Information Engineering, Changchun University（长春大学电子与信息工程学院）
Shaanxi Normal University（陕西师范大学）；Nanjing University of Science and Technology（南京理工大学）；Harbin Institute of Technology（哈尔滨工业大学）
Recent years have witnessed the great success of deep convolutional neural networks (CNNs) in image denoising. Albeit deeper network and larger model capacity generally benefit performance, it remains a challenging practical issue to train a very deep image denoising network. Using multilevel wavelet-CNN (MWCNN) as an example, we empirically find that the denoising performance cannot be significantly improved by either increasing wavelet decomposition levels or increasing convolution layers within each level. To cope with this issue, this paper presents a multi-level wavelet residual network (…
School of Basic Medical Science, Fudan University（复旦大学基础医学院）；Shanghai Key Laboratory of Medical Image Computing and Computer Assited Intervention（上海市医学图像计算与计算机辅助干预重点实验室）
We propose an unsupervised image fusion architecture for multiple application scenarios based on the combination of multi-scale discrete wavelet transform through regional energy and deep learning. To our best knowledge, this is the first time the conventional image fusion method has been combined with deep learning. The useful information of feature maps can be utilized adequately through multi-scale discrete wavelet transform in our proposed method.Compared with other state-of-the-art fusion method, the proposed algorithm exhibits better fusion performance in both subjective and objective ev…
Convolutional neural network (CNN), with ability of feature learning and nonlinear mapping, has demonstrated its effectiveness in prognostics and health management (PHM). However, explanation on the physical meaning of a CNN architecture has rarely been studied. In this paper, a novel wavelet driven deep neural network termed as WaveletKernelNet (WKN) is presented, where a continuous wavelet convolutional (CWConv) layer is designed to replace the first convolutional layer of the standard CNN. This enables the first CWConv layer to discover more meaningful filters. Furthermore, only the scale p…
The wavelet shrinkage denoising approach is able to maintain local regularity of a signal while suppressing noise. However, the conventional wavelet shrinkage based methods are not time-scale adaptive to track the local time-scale variation. In this paper, a new type of Neural Shrinkage (NS) is presented with a new class of shrinkage architecture for speckle reduction in Synthetic Aperture Radar (SAR) images. The numerical results indicate that the new method outperforms the standard filters, the standard wavelet shrinkage despeckling method, and previous NS.
Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）；Seoul National University Bundang Hospital（首尔国立大学盆唐医院）
Model based iterative reconstruction (MBIR) algorithms for low-dose X-ray CT are computationally expensive. To address this problem, we recently proposed a deep convolutional neural network (CNN) for low-dose X-ray CT and won the second place in 2016 AAPM Low-Dose CT Grand Challenge. However, some of the texture were not fully recovered. To address this problem, here we propose a novel framelet-based denoising algorithm using wavelet residual network which synergistically combines the expressive power of deep learning and the performance guarantee from the framelet-based denoising algorithms. …
This paper examines the possibility of, and the possible advantages to learning the filters of convolutional neural networks (CNNs) for image analysis in the wavelet domain. We are stimulated by both Mallat's scattering transform and the idea of filtering in the Fourier domain. It is important to explore new spaces in which to learn, as these may provide inherent advantages that are not available in the pixel space. However, the scattering transform is limited by its inability to learn in between scattering orders, and any Fourier domain filtering is limited by the large number of filter param…
Uncertainty-Aware Source-Free Adaptive Image Super-Resolution with Wavelet Augmentation Transformer
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；University of Science and Technology of China（中国科学技术大学）；OPPO Research Institute（OPPO研究院）；The Hong Kong Polytechnic University（香港理工大学）；ShanghaiTech University（上海科技大学）
Cornell University（康奈尔大学）；Indian Institute of Information Technology, Allahabad（阿拉哈巴德印度信息技术学院）；Indian Institute of Science Education and Research - Kolkata（加尔各答印度科学教育与研究学院）
The paper presents a non-uniform quantization method for the Detail components in the JPEG2000 standard. Incorporating the fact that the coefficients lying towards the ends of the histogram plot of each Detail component represent the structural information of an image, the quantization step sizes become smaller at they approach the ends of the histogram plot. The variable quantization step sizes are determined by the actual statistics of the wavelet coefficients. Mean and standard deviation are the two statistical parameters used iteratively to obtain the variable step sizes. Moreover, the mea…
Due to the potential risk of inducing cancers, radiation dose of X-ray CT should be reduced for routine patient scanning. However, in low-dose X-ray CT, severe artifacts usually occur due to photon starvation, beamhardening, etc, which decrease the reliability of diagnosis. Thus, high quality reconstruction from low-dose X-ray CT data has become one of the important research topics in CT community. Conventional model-based denoising approaches are, however, computationally very expensive, and image domain denoising approaches hardly deal with CT specific noise patterns. To address these issues…
Universität Bonn（波恩大学）；Fraunhofer SCAI（弗劳恩霍夫算法与科学计算研究所）；University of Bonn（波恩大学）；Fraunhofer Center for Machine Learning（弗劳恩霍夫机器学习中心）；Fraunhofer ITWM（弗劳恩霍夫工业数学研究所）；Institute for Numerical Simulation（数值模拟研究所）
As neural networks become able to generate realistic artificial images, they have the potential to improve movies, music, video games and make the internet an even more creative and inspiring place. Yet, the latest technology potentially enables new digital ways to lie. In response, the need for a diverse and reliable method toolbox arises to identify artificial images and other content. Previous work primarily relies on pixel-space CNNs or the Fourier transform. To the best of our knowledge, synthesized fake image analysis and detection methods based on a multi-scale wavelet representation, l…
Model based iterative reconstruction (MBIR) algorithms for low-dose X-ray CT are computationally complex because of the repeated use of the forward and backward projection. Inspired by this success of deep learning in computer vision applications, we recently proposed a deep convolutional neural network (CNN) for low-dose X-ray CT and won the second place in 2016 AAPM Low-Dose CT Grand Challenge. However, some of the texture are not fully recovered, which was unfamiliar to some radiologists. To cope with this problem, here we propose a direct residual learning approach on directional wavelet d…
WaveGuard: Robust Deepfake Detection and Source Tracing via Dual-Tree Complex Wavelet and Graph Neural Networks
College of Computer Science and Technology, Xinjiang University（新疆大学计算机科学与技术学院）；Xinjiang Multimodal Intelligent Processing and Information Security Engineering Technology Research Center（新疆多模态智能处理与信息安全工程技术研究中心）；College of Computer Science and Electronic Engineering, Hunan University（湖南大学计算机科学与电子工程学院）；School of Computer Science, Hefei University of Technology（合肥工业大学计算机科学与技术学院）
