Data-agnostic quasi-imperceptible perturbations on inputs are known to degrade recognition accuracy of deep convolutional networks severely. This phenomenon is considered to be a potential security issue. Moreover, some results on statistical generalization guarantees indicate that the phenomenon can be a key to improve the networks' generalization. However, the characteristics of the shared directions of such harmful perturbations remain unknown. Our primal finding is that convolutional networks are sensitive to the directions of Fourier basis functions. We derived the property by specializing a hypothesis of the cause of the sensitivity, known as the linearity of neural networks, to convolutional networks and empirically validated it. As a by-product of the analysis, we propose an algorithm to create shift-invariant universal adversarial perturbations available in black-box settings.
We investigate the performance of modern convolutional neural networks (CNN) and a linear support vector machine (SVM) with respect to spatial contrast sensitivity. Specifically, we compare CNN sensitivity to that of a Bayesian ideal observer (IO) with the signal-known-exactly and noise known statistically. A ResNet-18 reaches optimal performance for harmonic patterns, as well as several classes of real world signals including faces. For these stimuli the CNN substantially outperforms the SVM. We further analyzed the case in which the signal might appear in one of multiple locations and found …
Texas Tech University（得克萨斯理工大学）；Georgia Institute of Technology（佐治亚理工学院）；State University of New York at Buffalo（纽约州立大学布法罗分校）
This paper proposes to use Fast Fourier Transformation-based U-Net (a refined fully convolutional networks) and perform image convolution in neural networks. Leveraging the Fast Fourier Transformation, it reduces the image convolution costs involved in the Convolutional Neural Networks (CNNs) and thus reduces the overall computational costs. The proposed model identifies the object information from the images. We apply the Fast Fourier transform algorithm on an image data set to obtain more accessible information about the image data, before segmenting them through the U-Net architecture. More…
Indian Institute of Technology Gandhinagar（印度理工学院甘地纳格尔分校）
In this paper, we propose a new convolutional layer called Depthwise-STFT Separable layer that can serve as an alternative to the standard depthwise separable convolutional layer. The construction of the proposed layer is inspired by the fact that the Fourier coefficients can accurately represent important features such as edges in an image. It utilizes the Fourier coefficients computed (channelwise) in the 2D local neighborhood (e.g., 3x3) of each position of the input map to obtain the feature maps. The Fourier coefficients are computed using 2D Short Term Fourier Transform (STFT) at multipl…
This paper presents a significant improvement for the synthesis of texture images using convolutional neural networks (CNNs), making use of constraints on the Fourier spectrum of the results. More precisely, the texture synthesis is regarded as a constrained optimization problem, with constraints conditioning both the Fourier spectrum and statistical features learned by CNNs. In contrast with existing methods, the presented method inherits from previous CNN approaches the ability to depict local structures and fine scale details, and at the same time yields coherent large scale structures, eve…
Friedrich Schiller University Jena（耶拿弗里德里希·席勒大学）；University of Edinburgh（爱丁堡大学）
In this paper, we study the sensitivity of CNN outputs with respect to image transformations and noise in the area of fine-grained recognition. In particular, we answer the following questions (1) how sensitive are CNNs with respect to image transformations encountered during wild image capture?; (2) how can we predict CNN sensitivity?; and (3) can we increase the robustness of CNNs with respect to image degradations? To answer the first question, we provide an extensive empirical sensitivity analysis of commonly used CNN architectures (AlexNet, VGG19, GoogleNet) across various types of image …
Institute for Infocomm Research, A*STAR（新加坡科技研究局资讯通信研究院）；School of Computing, National University of Singapore（新加坡国立大学计算学院）；Institute of Data Science, National University of Singapore（新加坡国立大学数据科学研究所）；Centre for Frontier AI Research, A*STAR（新加坡科技研究局前沿人工智能研究中心）
Recent work has empirically shown that deep neural networks latch on to the Fourier statistics of training data and show increased sensitivity to Fourier-basis directions in the input. Understanding and modifying this Fourier-sensitivity of computer vision models may help improve their robustness. Hence, in this paper we study the frequency sensitivity characteristics of deep neural networks using a principled approach. We first propose a basis trick, proving that unitary transformations of the input-gradient of a function can be used to compute its gradient in the basis induced by the transfo…
A Fast Fourier Convolutional Deep Neural Network For Accurate and Explainable Discrimination Of Wheat Yellow Rust And Nitrogen Deficiency From Sentinel-2 Time-Series Data
The University of Leeds（利兹大学）；Manchester Metropolitan University（曼彻斯特城市大学）；University of Córdoba（科尔多瓦大学）；The University of Manchester（曼彻斯特大学）；Beijing University of Technology（北京工业大学）；Yangzhou University（扬州大学）
University of Toronto（多伦多大学）；LG AI Research（LG人工智能研究院）
Visualizing the features captured by Convolutional Neural Networks (CNNs) is one of the conventional approaches to interpret the predictions made by these models in numerous image recognition applications. Grad-CAM is a popular solution that provides such a visualization by combining the activation maps obtained from the model. However, the average gradient-based terms deployed in this method underestimates the contribution of the representations discovered by the model to its predictions. Addressing this problem, we introduce a solution to tackle this issue by computing the path integral of t…
Indian Institute of Technology Gandhinagar（印度理工学院甘地讷格尔分校）；Osaka University（大阪大学）
Conventional 3D convolutional neural networks (CNNs) are computationally expensive, memory intensive, prone to overfitting, and most importantly, there is a need to improve their feature learning capabilities. To address these issues, we propose spatio-temporal short term Fourier transform (STFT) blocks, a new class of convolutional blocks that can serve as an alternative to the 3D convolutional layer and its variants in 3D CNNs. An STFT block consists of non-trainable convolution layers that capture spatially and/or temporally local Fourier information using a STFT kernel at multiple low freq…
Southeast University（东南大学）；The first affiliated hospital of Nanjing medical university（南京医科大学第一附属医院）；Centre de Recherche en Information Biomédicale Sino-Français (CRIBs)（中法生物医学信息研究中心（CRIBs））；University of Western Ontario（西安大略大学）
Reliable automatic classification of colonoscopy images is of great significance in assessing the stage of colonic lesions and formulating appropriate treatment plans. However, it is challenging due to uneven brightness, location variability, inter-class similarity, and intra-class dissimilarity, affecting the classification accuracy. To address the above issues, we propose a Fourier-based Frequency Complex Network (FFCNet) for colon disease classification in this study. Specifically, FFCNet is a novel complex network that enables the combination of complex convolutional networks with frequenc…
The segmentation of retinal vessels is of significance for doctors to diagnose the fundus diseases. However, existing methods have various problems in the segmentation of the retinal vessels, such as insufficient segmentation of retinal vessels, weak anti-noise interference ability, and sensitivity to lesions, etc. Aiming to the shortcomings of existed methods, this paper proposes the use of conditional deep convolutional generative adversarial networks to segment the retinal vessels. We mainly improve the network structure of the generator. The introduction of the residual module at the convo…
The application of convolutional neural networks (ConvNets) to harness high-content screening images or 2D compound representations is gaining increasing attention in drug discovery. However, existing applications often require large data sets for training, or sophisticated pretraining schemes. Here, we show using 33 IC50 data sets from ChEMBL 23 that the in vitro activity of compounds on cancer cell lines and protein targets can be accurately predicted on a continuous scale from their Kekule structure representations alone by extending existing architectures, which were pretrained on unrelate…
We introduce a unified framework for group equivariant networks on homogeneous spaces derived from a Fourier perspective. We consider tensor-valued feature fields, before and after a convolutional layer. We present a unified derivation of kernels via the Fourier domain by leveraging the sparsity of Fourier coefficients of the lifted feature fields. The sparsity emerges when the stabilizer subgroup of the homogeneous space is a compact Lie group. We further introduce a nonlinear activation, via an elementwise nonlinearity on the regular representation after lifting and projecting back to the fi…
Fast Fourier Convolutional GAN for 30 m Clear-Sky Land Surface Temperature Gap-Free Reconstruction
Technical University of Munich（慕尼黑工业大学）；Helmholtz Centre for Polar and Marine Research, Alfred Wegener Institute（亥姆霍兹极地与海洋研究中心阿尔弗雷德·韦格纳研究所）；Swiss Federal Institute of Technology Zurich (ETH Zurich)（瑞士联邦理工学院苏黎世分校）
Deep Learning-based Computer Vision field has recently been trying to explore larger kernels for convolution to effectively scale up Convolutional Neural Networks. Simultaneously, new paradigm of models such as Vision Transformers find it difficult to scale up to larger higher resolution images due to their quadratic complexity in terms of input sequence. In this report, Fast Fourier Transform is utilised in various ways to provide some solutions to these issues.
Using Frame Theoretic Convolutional Gridding for Robust Synthetic Aperture Sonar Imaging
Department of Electrical Engineering, Pennsylvania State University, State College, PA（电气工程系，宾夕法尼亚州立大学，州立学院，PA）；Department of Mathematics, Dartmouth College, Hanover, NH（数学系，达特茅斯学院，汉诺威，NH）；U.S. Naval Research Laboratory, Washington, DC（美国海军研究实验室，华盛顿，DC）
Friedrich-Alexander University Erlangen-Nürnberg（埃尔朗根-纽伦堡弗里德里希-亚历山大大学）；Siemens Healthcare GmbH（西门子医疗有限公司）
Purpose: To develop an algorithm for robust partial Fourier (PF) reconstruction applicable to diffusion-weighted (DW) images with non-smooth phase variations. Methods: Based on an unrolled proximal splitting algorithm, a neural network architecture is derived which alternates between data consistency operations and regularization implemented by recurrent convolutions. In order to exploit correlations, multiple repetitions of the same slice are jointly reconstructed under consideration of permutation-equivariance. The algorithm is trained on DW liver data of 60 volunteers and evaluated on retro…
We propose Absum, which is a regularization method for improving adversarial robustness of convolutional neural networks (CNNs). Although CNNs can accurately recognize images, recent studies have shown that the convolution operations in CNNs commonly have structural sensitivity to specific noise composed of Fourier basis functions. By exploiting this sensitivity, they proposed a simple black-box adversarial attack: Single Fourier attack. To reduce structural sensitivity, we can use regularization of convolution filter weights since the sensitivity of linear transform can be assessed by the nor…
Hefei Institute of Physical Science, Chinese Academy of Sciences（中国科学院合肥物质科学研究院）；University of Science and Technology of China（中国科学技术大学）；SenseBrain Technology (SenseTime Research USA)（商汤美国研究院思脑科技）；Nanyang Technological University（南洋理工大学）；Xi’an Jiaotong University（西安交通大学）；Pazhou Laboratory (Huangpu)（琶洲实验室（黄埔））
Existing convolutional neural networks widely adopt spatial down-/up-sampling for multi-scale modeling. However, spatial up-sampling operators (\emph{e.g.}, interpolation, transposed convolution, and un-pooling) heavily depend on local pixel attention, incapably exploring the global dependency. In contrast, the Fourier domain obeys the nature of global modeling according to the spectral convolution theorem. Unlike the spatial domain that performs up-sampling with the property of local similarity, up-sampling in the Fourier domain is more challenging as it does not follow such a local property.…
Huazhong University of Science and Technology（华中科技大学）；The Central Hospital of Wuhan（武汉市中心医院）；JD AI Research（京东人工智能研究院）；Hong Kong University of Science and Technology（香港科技大学）
Automated methods for detecting pulmonary embolisms (PEs) on CT pulmonary angiography (CTPA) images are of high demand. Existing methods typically employ separate steps for PE candidate detection and false positive removal, without considering the ability of the other step. As a result, most existing methods usually suffer from a high false positive rate in order to achieve an acceptable sensitivity. This study presents an end-to-end trainable convolutional neural network (CNN) where the two steps are optimized jointly. The proposed CNN consists of three concatenated subnets: 1) a novel 3D can…
UCLA（加州大学洛杉矶分校）；Dana-Farber Cancer Institute（丹娜-法伯癌症研究所）；Brigham and Women’s Hospital（布莱根和妇女医院）；Harvard Medical School（哈佛医学院）
Purpose: Provide a closed-form solution to the sinusoidal coil sensitivity model proposed by Kern et al. Solution allows for the precise computations of varied, simulated bias fields which can be directly applied onto raw intensity datasets. Methods: Fourier distribution theory and standard integration techniques were used to calculate the Fourier transform of measured magnetic field produced from line segment sources. Results: A $L^1_{\rm loc}(\mathbb{R}^3)$ function is derived in full generality for arbitrary line segment geometries. Sampling criteria and equivalence to the original sinusoid…
Isfahan University of Technology（伊斯法罕理工大学）；McMaster University（麦克马斯特大学）
Convolutional neural networks (CNNs) have a large number of variables and hence suffer from a complexity problem for their implementation. Different methods and techniques have developed to alleviate the problem of CNN's complexity, such as quantization, pruning, etc. Among the different simplification methods, computation in the Fourier domain is regarded as a new paradigm for the acceleration of CNNs. Recent studies on Fast Fourier Transform (FFT) based CNN aiming at simplifying the computations required for FFT. However, there is a lot of space for working on the reduction of the computatio…
Bilkent University（比尔肯特大学）；Institute for Infocomm Research（信息通信研究院）；KK Women's and Children's Hospital（KK妇女儿童医院）
This work aims to develop an end-to-end solution for seizure onset detection. We design the SeizNet, a Convolutional Neural Network for seizure detection. To compare SeizNet with traditional machine learning approach, a baseline classifier is implemented using spectrum band power features with Support Vector Machines (BPsvm). We explore the possibility to use the least number of channels for accurate seizure detection by evaluating SeizNet and BPsvm approaches using all channels and two channels settings respectively. EEG Data is acquired from 29 pediatric patients admitted to KK Woman's and C…
Institute of Physics（物理研究所）；École Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）
A central question of machine learning is how deep nets manage to learn tasks in high dimensions. An appealing hypothesis is that they achieve this feat by building a representation of the data where information irrelevant to the task is lost. For image datasets, this view is supported by the observation that after (and not before) training, the neural representation becomes less and less sensitive to diffeomorphisms acting on images as the signal propagates through the net. This loss of sensitivity correlates with performance, and surprisingly correlates with a gain of sensitivity to white no…
We develop three efficient approaches for generating visual explanations from 3D convolutional neural networks (3D-CNNs) for Alzheimer's disease classification. One approach conducts sensitivity analysis on hierarchical 3D image segmentation, and the other two visualize network activations on a spatial map. Visual checks and a quantitative localization benchmark indicate that all approaches identify important brain parts for Alzheimer's disease diagnosis. Comparative analysis show that the sensitivity analysis based approach has difficulty handling loosely distributed cerebral cortex, and appr…
Carnegie Mellon University（卡内基梅隆大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Performance of neural networks can be significantly improved by encoding known invariance for particular tasks. Many image classification tasks, such as those related to cellular imaging, exhibit invariance to rotation. We present a novel scheme using the magnitude response of the 2D-discrete-Fourier transform (2D-DFT) to encode rotational invariance in neural networks, along with a new, efficient convolutional scheme for encoding rotational equivariance throughout convolutional layers. We implemented this scheme for several image classification tasks and demonstrated improved performance, in …
Computed tomography (CT) generates a stack of cross-sectional images covering a region of the body. The visual assessment of these images for the identification of potential abnormalities is a challenging and time consuming task due to the large amount of information that needs to be processed. In this article we propose a deep artificial neural network architecture, ReCTnet, for the fully-automated detection of pulmonary nodules in CT scans. The architecture learns to distinguish nodules and normal structures at the pixel level and generates three-dimensional probability maps highlighting are…
Filters in a Convolutional Neural Network (CNN) contain model parameters learned from enormous amounts of data. In this paper, we suggest to decompose convolutional filters in CNN as a truncated expansion with pre-fixed bases, namely the Decomposed Convolutional Filters network (DCFNet), where the expansion coefficients remain learned from data. Such a structure not only reduces the number of trainable parameters and computation, but also imposes filter regularity by bases truncation. Through extensive experiments, we consistently observe that DCFNet maintains accuracy for image classification…
University of Chinese Academy of Sciences（中国科学院大学）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Nanchang University（南昌大学）
Parallel imaging has been an essential technique to accelerate MR imaging. Nevertheless, the acceleration rate is still limited due to the ill-condition and challenges associated with the undersampled reconstruction. In this paper, we propose a model-based convolutional de-aliasing network with adaptive parameter learning to achieve accurate reconstruction from multi-coil undersampled k-space data. Three main contributions have been made: a de-aliasing reconstruction model was proposed to accelerate parallel MR imaging with deep learning exploring both spatial redundancy and multi-coil correla…
Minia University（米尼亚大学）；Nahda University in Beni-Suef（贝尼苏韦夫复兴大学）；American University in the Emirates（阿联酋美国大学）
Despite the great efforts to find an effective way for COVID-19 prediction, the virus nature and mutation represent a critical challenge to diagnose the covered cases. However, developing a model to predict COVID-19 via Chest X-Ray (CXR) images with accurate performance is necessary to help in early diagnosis. In this paper, a hybrid quantum-classical convolutional Neural Networks (HQCNN) model used the random quantum circuits (RQCs) as a base to detect COVID-19 patients with CXR images. A collection of 6952 CXR images, including 1161 COVID-19, 1575 normal, and 5216 pneumonia images, were used…
Fraunhofer ITWM（弗劳恩霍夫工业数学研究所）；University of Kaiserslautern（凯泽斯劳滕大学）；Fraunhofer Center Machine Learning（弗劳恩霍夫机器学习中心）；University of Mannheim（曼海姆大学）；Offenburg University（奥芬堡大学）
Despite the success of convolutional neural networks (CNNs) in many computer vision and image analysis tasks, they remain vulnerable against so-called adversarial attacks: Small, crafted perturbations in the input images can lead to false predictions. A possible defense is to detect adversarial examples. In this work, we show how analysis in the Fourier domain of input images and feature maps can be used to distinguish benign test samples from adversarial images. We propose two novel detection methods: Our first method employs the magnitude spectrum of the input images to detect an adversarial…
University of Groningen（格罗宁根大学）；University Medical Center Groningen（格罗宁根大学医学中心）；University of Twente（特文特大学）
Objective: In clinical practice, small lung nodules can be easily overlooked by radiologists. The paper aims to provide an efficient and accurate detection system for small lung nodules while keeping good performance for large nodules. Methods: We propose a multi-planar detection system using convolutional neural networks. The 2-D convolutional neural network model, U-net++, was trained by axial, coronal, and sagittal slices for the candidate detection task. All possible nodule candidates from the three different planes are combined. For false positive reduction, we apply 3-D multi-scale dense…
Courant Institute of Mathematical Sciences（库朗数学科学研究所）；New York University（纽约大学）
Convolutional networks are one of the most widely employed architectures in computer vision and machine learning. In order to leverage their ability to learn complex functions, large amounts of data are required for training. Training a large convolutional network to produce state-of-the-art results can take weeks, even when using modern GPUs. Producing labels using a trained network can also be costly when dealing with web-scale datasets. In this work, we present a simple algorithm which accelerates training and inference by a significant factor, and can yield improvements of over an order of…
Proportional Sensitivity in Generative Adversarial Network (GAN)-Augmented Brain Tumor Classification Using Convolutional Neural Network
American International University-Bangladesh（美国国际大学-孟加拉国）；Asian University of Bangladesh（孟加拉国亚洲大学）；Information and Computer Science Department, King Fahd University of Petroleum and Minerals (KFUPM)（石油和矿物大学（KFUPM）信息与计算机科学系）；SDAIA-KFUPM Joint Research Center for AI, King Fahd University of Petroleum and Minerals（人工智能联合研究中心（SDAIA-KFUPM）, 石油和矿物大学）；Interdisciplinary Research Center for Bio Systems and Machines, King Fahd University of Petroleum and Minerals（生物系统与机器交叉研究中心，石油和矿物大学）；Independent University, Bangladesh（独立大学）
Enhancing mTBI Diagnosis with Residual Triplet Convolutional Neural Network Using 3D CT
School of Electrical Engineering and Computer Science, University of Queensland（昆士兰大学电气工程与计算机科学学院）；The Centre for Advanced Imaging, Australian Institute for Bioengineering and Nanotechnology, University of Queensland（昆士兰大学高级成像中心，澳大利亚生物工程与纳米技术研究所）；ARC Training Centre for Innovation in Biomedical Imaging Technology（ARC生物医学成像技术创新培训中心）
COVID-19 is an infectious disease that causes respiratory problems similar to those caused by SARS-CoV (2003). Currently, swab samples are being used for its diagnosis. The most common testing method used is the RT-PCR method, which has high specificity but variable sensitivity. AI-based detection has the capability to overcome this drawback. In this paper, we propose a prospective method wherein we use chest CT scans to diagnose the patients for COVID-19 pneumonia. We use a set of open-source images, available as individual CT slices, and full CT scans from a private Indian Hospital to train …
Automatization of the diagnosis of any kind of disease is of great importance and it's gaining speed as more and more deep learning solutions are applied to different problems. One of such computer aided systems could be a decision support too able to accurately differentiate between different types of breast cancer histological images - normal tissue or carcinoma. In this paper authors present a deep learning solution, based on convolutional capsule network for classification of four types of images of breast tissue biopsy when hematoxylin and eusin staining is applied. The cross-validation a…
