Image quality assessment (IQA) plays a fundamental role in evaluating image processing. Currently, JPEG AIC specifies the IQA methods, dividing them into three levels: AIC-1, 2, and 3. AIC-1 measures the quality from low to high, AIC-2 focuses on the threshold for visual losslessness, and AIC-3 measures the range between 1 and 2. AIC-3 requires complex processing and many comparisons, such as using boosted triplets to obtain highly accurate JNDs and then using those JNDs to create scale scores, or generating many combinations of triplets. In this study, we revisit the definition and propose a method for measuring the target band of AIC-3 by mixing the measurement methods of AIC-1 and AIC-2 and adjusting the sensitivity. This method presents the pristine and degraded images and asks whether they are the same or not. We called this absolute binary decision (ABD), referring to ACR in AIC-1. We constructed a JPEG-specific IQA dataset using ABD from distorted images that were progressively patched to relate the patches to the IQA of the entire images. As this was a new experiment, it was first conducted under laboratory control to ensure reliability. The experimental results showed that ABD could measure the QP40-90 range. In addition, it was found that patching differs from the entire image case. While patching draws attention to places that people do not usually pay attention to, usual image presentation concentrates attention through semantic guidance, suggesting the possibility that pseudo-attention patching is being performed on characteristic locations.
{"title":"A Multi-Level Patch Dataset for JPEG Image Quality Assessment by Absolute Binary Decision","authors":"Soichiro Honda;Yoshihiro Maeda;Osamu Watanabe;Norishige Fukushima","doi":"10.1109/OJSP.2025.3571674","DOIUrl":"https://doi.org/10.1109/OJSP.2025.3571674","url":null,"abstract":"Image quality assessment (IQA) plays a fundamental role in evaluating image processing. Currently, JPEG AIC specifies the IQA methods, dividing them into three levels: AIC-1, 2, and 3. AIC-1 measures the quality from low to high, AIC-2 focuses on the threshold for visual losslessness, and AIC-3 measures the range between 1 and 2. AIC-3 requires complex processing and many comparisons, such as using boosted triplets to obtain highly accurate JNDs and then using those JNDs to create scale scores, or generating many combinations of triplets. In this study, we revisit the definition and propose a method for measuring the target band of AIC-3 by mixing the measurement methods of AIC-1 and AIC-2 and adjusting the sensitivity. This method presents the pristine and degraded images and asks whether they are the same or not. We called this absolute binary decision (ABD), referring to ACR in AIC-1. We constructed a JPEG-specific IQA dataset using ABD from distorted images that were progressively patched to relate the patches to the IQA of the entire images. As this was a new experiment, it was first conducted under laboratory control to ensure reliability. The experimental results showed that ABD could measure the QP40-90 range. In addition, it was found that patching differs from the entire image case. While patching draws attention to places that people do not usually pay attention to, usual image presentation concentrates attention through semantic guidance, suggesting the possibility that pseudo-attention patching is being performed on characteristic locations.","PeriodicalId":73300,"journal":{"name":"IEEE open journal of signal processing","volume":"6 ","pages":"631-640"},"PeriodicalIF":2.9,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11007521","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144367073","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-19DOI: 10.1109/OJSP.2025.3571681
Nupur Thakur;Yuzhen Ding;Baoxin Li
The vulnerability of deep neural networks to adversarial attacks has attracted much research effort. Still, studies have shown that it is challenging to simultaneously achieve both strong robustness to adversarial attacks and low degradation in the performance on the original task, as there is always a trade-off between the two objectives. In this paper, we present a novel training strategy named Adversarial-Free Defense (AFD), which introduces a minimal change to a network architecture (by modifying the first convolution layer) while employing a learning algorithm that leads to special properties of the first-layer kernels. We show how this learning strategy enhances the robustness of the network to adversarial attacks (without using adversarial samples) while maintaining a reasonable performance on the original task. Empirical results including analysis in terms of the effective Lipschitz constant of the learned network suggest that, compared to most existing methods that rely on elaborate regularization schemes imposed on all layers, our seemingly simplistic approach demonstrates high effectiveness.
{"title":"AFD: Defending Convolutional Neural Networks Without Using Adversarial Samples","authors":"Nupur Thakur;Yuzhen Ding;Baoxin Li","doi":"10.1109/OJSP.2025.3571681","DOIUrl":"https://doi.org/10.1109/OJSP.2025.3571681","url":null,"abstract":"The vulnerability of deep neural networks to adversarial attacks has attracted much research effort. Still, studies have shown that it is challenging to simultaneously achieve both strong robustness to adversarial attacks and low degradation in the performance on the original task, as there is always a trade-off between the two objectives. In this paper, we present a novel training strategy named Adversarial-Free Defense (AFD), which introduces a minimal change to a network architecture (by modifying the first convolution layer) while employing a learning algorithm that leads to special properties of the first-layer kernels. We show how this learning strategy enhances the robustness of the network to adversarial attacks (without using adversarial samples) while maintaining a reasonable performance on the original task. Empirical results including analysis in terms of the effective Lipschitz constant of the learned network suggest that, compared to most existing methods that rely on elaborate regularization schemes imposed on all layers, our seemingly simplistic approach demonstrates high effectiveness.","PeriodicalId":73300,"journal":{"name":"IEEE open journal of signal processing","volume":"6 ","pages":"571-580"},"PeriodicalIF":2.9,"publicationDate":"2025-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11007011","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144243740","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-10DOI: 10.1109/OJSP.2025.3549350
Lukas Schynol;Marius Pesavento
Anomaly detection (AD) is increasingly recognized as a key component for ensuring the resilience of future communication systems. While deep learning has shown state-of-the-art AD performance, its application in critical systems is hindered by concerns regarding training data efficiency, domain adaptation and interpretability. This work considers AD in network flows using incomplete measurements, leveraging a robust tensor decomposition approach and deep unrolling techniques to address these challenges. We first propose a novel block-successive convex approximation algorithm based on a regularized model-fitting objective where the normal flows are modeled as low-rank tensors and anomalies as sparse. An augmentation of the objective is introduced to decrease the computational cost. We apply deep unrolling to derive a novel deep network architecture based on our proposed algorithm, treating the regularization parameters as learnable weights. Inspired by Bayesian approaches, we extend the model architecture to perform online adaptation to per-flow and per-time-step statistics, improving AD performance while maintaining a low parameter count and preserving the problem's permutation equivariances. To optimize the deep network weights for detection performance, we employ a homotopy optimization approach based on an efficient approximation of the area under the receiver operating characteristic curve. Extensive experiments on synthetic and real-world data demonstrate that our proposed deep network architecture exhibits a high training data efficiency, outperforms reference methods, and adapts seamlessly to varying network topologies.
{"title":"Adaptive Anomaly Detection in Network Flows With Low-Rank Tensor Decompositions and Deep Unrolling","authors":"Lukas Schynol;Marius Pesavento","doi":"10.1109/OJSP.2025.3549350","DOIUrl":"https://doi.org/10.1109/OJSP.2025.3549350","url":null,"abstract":"Anomaly detection (AD) is increasingly recognized as a key component for ensuring the resilience of future communication systems. While deep learning has shown state-of-the-art AD performance, its application in critical systems is hindered by concerns regarding training data efficiency, domain adaptation and interpretability. This work considers AD in network flows using incomplete measurements, leveraging a robust tensor decomposition approach and deep unrolling techniques to address these challenges. We first propose a novel block-successive convex approximation algorithm based on a regularized model-fitting objective where the normal flows are modeled as low-rank tensors and anomalies as sparse. An augmentation of the objective is introduced to decrease the computational cost. We apply deep unrolling to derive a novel deep network architecture based on our proposed algorithm, treating the regularization parameters as learnable weights. Inspired by Bayesian approaches, we extend the model architecture to perform online adaptation to per-flow and per-time-step statistics, improving AD performance while maintaining a low parameter count and preserving the problem's permutation equivariances. To optimize the deep network weights for detection performance, we employ a homotopy optimization approach based on an efficient approximation of the area under the receiver operating characteristic curve. Extensive experiments on synthetic and real-world data demonstrate that our proposed deep network architecture exhibits a high training data efficiency, outperforms reference methods, and adapts seamlessly to varying network topologies.","PeriodicalId":73300,"journal":{"name":"IEEE open journal of signal processing","volume":"6 ","pages":"417-433"},"PeriodicalIF":2.9,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10918821","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143896493","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-09DOI: 10.1109/OJSP.2025.3568675
Yen-Ming Chen;Wei-Lun Lin;Heng Lee;Tsung-Lin Chen
Spatial Modulation (SM) and Generalized Spatial Modulation (GSM) have attracted significant attention in the development of spectrally and energy-efficient transmission schemes for multiple-input multiple-output (MIMO) systems. However, independently designing the constellation cardinality and TACs leads to limited performance gains and an exponential increase in complexity, particularly under maximum-likelihood (ML) detection. To address these limitations, the generalized block-based spatial modulation (GBSM) scheme was proposed, enabling greater flexibility by jointly designing GSM signals across a block of time indices. Building on this idea, this paper first proposes a near-optimal codebook search method based on three-dimensional (3-D) mapping, applicable to both fast and slow Rayleigh fading channels. Secondly, a codebook-assisted tree-search detector (CATSD) is introduced, offering a 98% reduction in complexity compared to ML detection while maintaining near-ML error performance. Finally, an alternative codebook search method is presented, accompanied by a complexity analysis that reveals a favorable trade-off between performance and computational cost.
{"title":"On the Design of Near-Optimal Generalized Block-Based Spatial Modulation With Low Detection Complexity","authors":"Yen-Ming Chen;Wei-Lun Lin;Heng Lee;Tsung-Lin Chen","doi":"10.1109/OJSP.2025.3568675","DOIUrl":"https://doi.org/10.1109/OJSP.2025.3568675","url":null,"abstract":"Spatial Modulation (SM) and Generalized Spatial Modulation (GSM) have attracted significant attention in the development of spectrally and energy-efficient transmission schemes for multiple-input multiple-output (MIMO) systems. However, independently designing the constellation cardinality and TACs leads to limited performance gains and an exponential increase in complexity, particularly under maximum-likelihood (ML) detection. To address these limitations, the generalized block-based spatial modulation (GBSM) scheme was proposed, enabling greater flexibility by jointly designing GSM signals across a block of time indices. Building on this idea, this paper first proposes a near-optimal codebook search method based on three-dimensional (3-D) mapping, applicable to both fast and slow Rayleigh fading channels. Secondly, a codebook-assisted tree-search detector (CATSD) is introduced, offering a 98% reduction in complexity compared to ML detection while maintaining near-ML error performance. Finally, an alternative codebook search method is presented, accompanied by a complexity analysis that reveals a favorable trade-off between performance and computational cost.","PeriodicalId":73300,"journal":{"name":"IEEE open journal of signal processing","volume":"6 ","pages":"555-570"},"PeriodicalIF":2.9,"publicationDate":"2025-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10994453","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144243737","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-09DOI: 10.1109/OJSP.2025.3568757
Xiang Gao;Xinmu Wang;Zhou Zhao;Junqi Huang;Xianfeng David Gu
Recent years have witnessed rapid advancements in 3D scanning technologies, with diverse applications spanning VR/AR, digital human creation, and medical imaging. Structured-light scanning with phase-shifting techniques is preferred for its use of non-radiative, low-intensity visible light and high accuracy, making it well suited for human-centric applications such as capturing 4D facial dynamics. A key step in these systems is phase unwrapping, which recovers continuous phase values from measurements that are inherently wrapped modulo $2pi$. The goal is to estimate the unwrapped phase count $k$, an integer-valued variable in the equation $Phi=phi + 2pi k$, where $phi$ is the wrapped phase and $Phi$ is the true phase. However, the presence of noise, occlusions, and piecewise continuous phase functions induced by complex 3D surface geometry makes the inverse reconstruction of the true phase extremely challenging. This is because phase unwrapping is an inherently ill-posed problem: measurements only provide modulo $2pi$ values, and recovering the correct unwrapped phase count requires strong assumptions about the smoothness or continuity of the underlying 3D surface. Existing methods typically involve a trade-off between speed and accuracy: Fast approaches lack precision, while accurate algorithms are too slow for real-time use. To overcome these limitations, this work proposes a novel phase unwrapping framework that reformulates GraphCut-based unwrapping as a pixel-labeling problem. This framework helps significantly improve the estimation of the unwrapped phase count $k$ through the invariance property of diffeomorphisms applied in image space via conformal and optimal transport (OT) maps. An odd number of diffeomorphisms are precomputed from the input phase data, and a hierarchical GraphCut algorithm is applied in each corresponding domain. The resulting label maps are fused via majority voting to efficiently and robustly estimate the unwrapped phase count $k$ at each pixel, using an odd number of votes to break ties. Experimental results demonstrate a 45.5× speedup and lower $L^{2}$ error in both real experiments and simulations, showing potential for real-time applications.
{"title":"Hierarchical GraphCut Phase Unwrapping Based on Invariance of Diffeomorphisms Framework","authors":"Xiang Gao;Xinmu Wang;Zhou Zhao;Junqi Huang;Xianfeng David Gu","doi":"10.1109/OJSP.2025.3568757","DOIUrl":"https://doi.org/10.1109/OJSP.2025.3568757","url":null,"abstract":"Recent years have witnessed rapid advancements in 3D scanning technologies, with diverse applications spanning VR/AR, digital human creation, and medical imaging. Structured-light scanning with phase-shifting techniques is preferred for its use of non-radiative, low-intensity visible light and high accuracy, making it well suited for human-centric applications such as capturing 4D facial dynamics. A key step in these systems is phase unwrapping, which recovers continuous phase values from measurements that are inherently wrapped modulo <inline-formula><tex-math>$2pi$</tex-math></inline-formula>. The goal is to estimate the unwrapped phase count <inline-formula><tex-math>$k$</tex-math></inline-formula>, an integer-valued variable in the equation <inline-formula><tex-math>$Phi=phi + 2pi k$</tex-math></inline-formula>, where <inline-formula><tex-math>$phi$</tex-math></inline-formula> is the wrapped phase and <inline-formula><tex-math>$Phi$</tex-math></inline-formula> is the true phase. However, the presence of noise, occlusions, and piecewise continuous phase functions induced by complex 3D surface geometry makes the inverse reconstruction of the true phase extremely challenging. This is because phase unwrapping is an inherently ill-posed problem: measurements only provide modulo <inline-formula><tex-math>$2pi$</tex-math></inline-formula> values, and recovering the correct unwrapped phase count requires strong assumptions about the smoothness or continuity of the underlying 3D surface. Existing methods typically involve a trade-off between speed and accuracy: Fast approaches lack precision, while accurate algorithms are too slow for real-time use. To overcome these limitations, this work proposes a novel phase unwrapping framework that reformulates GraphCut-based unwrapping as a pixel-labeling problem. This framework helps significantly improve the estimation of the unwrapped phase count <inline-formula><tex-math>$k$</tex-math></inline-formula> through the invariance property of diffeomorphisms applied in image space via conformal and optimal transport (OT) maps. An odd number of diffeomorphisms are precomputed from the input phase data, and a hierarchical GraphCut algorithm is applied in each corresponding domain. The resulting label maps are fused via majority voting to efficiently and robustly estimate the unwrapped phase count <inline-formula><tex-math>$k$</tex-math></inline-formula> at each pixel, using an odd number of votes to break ties. Experimental results demonstrate a 45.5× speedup and lower <inline-formula><tex-math>$L^{2}$</tex-math></inline-formula> error in both real experiments and simulations, showing potential for real-time applications.","PeriodicalId":73300,"journal":{"name":"IEEE open journal of signal processing","volume":"6 ","pages":"546-554"},"PeriodicalIF":2.9,"publicationDate":"2025-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10994451","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144178954","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-09DOI: 10.1109/OJSP.2025.3568758
Michael Neri;Tuomas Virtanen
Replay attacks belong to the class of severe threats against voice-controlled systems, exploiting the easy accessibility of speech signals by recorded and replayed speech to grant unauthorized access to sensitive data. In this work, we propose a multi-channel neural network architecture called M-ALRAD for the detection of replay attacks based on spatial audio features. This approach integrates a learnable adaptive beamformer with a convolutional recurrent neural network, allowing for joint optimization of spatial filtering and classification. Experiments have been carried out on the ReMASC dataset, which is a state-of-the-art multi-channel replay speech detection dataset encompassing four microphones with diverse array configurations and four environments. Results on the ReMASC dataset show the superiority of the approach compared to the state-of-the-art and yield substantial improvements for challenging acoustic environments. In addition, we demonstrate that our approach is able to better generalize to unseen environments with respect to prior studies.
{"title":"Multi-Channel Replay Speech Detection Using an Adaptive Learnable Beamformer","authors":"Michael Neri;Tuomas Virtanen","doi":"10.1109/OJSP.2025.3568758","DOIUrl":"https://doi.org/10.1109/OJSP.2025.3568758","url":null,"abstract":"Replay attacks belong to the class of severe threats against voice-controlled systems, exploiting the easy accessibility of speech signals by recorded and replayed speech to grant unauthorized access to sensitive data. In this work, we propose a multi-channel neural network architecture called M-ALRAD for the detection of replay attacks based on spatial audio features. This approach integrates a learnable adaptive beamformer with a convolutional recurrent neural network, allowing for joint optimization of spatial filtering and classification. Experiments have been carried out on the ReMASC dataset, which is a state-of-the-art multi-channel replay speech detection dataset encompassing four microphones with diverse array configurations and four environments. Results on the ReMASC dataset show the superiority of the approach compared to the state-of-the-art and yield substantial improvements for challenging acoustic environments. In addition, we demonstrate that our approach is able to better generalize to unseen environments with respect to prior studies.","PeriodicalId":73300,"journal":{"name":"IEEE open journal of signal processing","volume":"6 ","pages":"530-535"},"PeriodicalIF":2.9,"publicationDate":"2025-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10994395","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144117203","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-09DOI: 10.1109/OJSP.2025.3568756
Mariano V. Ntrougkas;Vasileios Mezaris;Ioannis Patras
The adoption of Deep Neural Networks (DNNs) in critical fields where predictions need to be accompanied by justifications is hindered by their inherent black-box nature. This paper introduces P-TAME (Perturbation-based Trainable Attention Mechanism for Explanations), a model-agnostic method for explaining DNN-based image classifiers. P-TAME employs an auxiliary image classifier to extract features from the input image, bypassing the need to tailor the explanation method to the internal architecture of the backbone classifier being explained. Unlike traditional perturbation-based methods, which have high computational requirements, P-TAME offers an efficient alternative by generating high-resolution explanations in a single forward pass during inference. We apply P-TAME to explain the decisions of VGG-16, ResNet-50, and ViT-B-16, three distinct and widely used image classifiers. Quantitative and qualitative results show that P-TAME matches or outperforms previous explainability methods, including model-specific ones.
{"title":"P-TAME: Explain Any Image Classifier With Trained Perturbations","authors":"Mariano V. Ntrougkas;Vasileios Mezaris;Ioannis Patras","doi":"10.1109/OJSP.2025.3568756","DOIUrl":"https://doi.org/10.1109/OJSP.2025.3568756","url":null,"abstract":"The adoption of Deep Neural Networks (DNNs) in critical fields where predictions need to be accompanied by justifications is hindered by their inherent black-box nature. This paper introduces P-TAME (Perturbation-based Trainable Attention Mechanism for Explanations), a model-agnostic method for explaining DNN-based image classifiers. P-TAME employs an auxiliary image classifier to extract features from the input image, bypassing the need to tailor the explanation method to the internal architecture of the backbone classifier being explained. Unlike traditional perturbation-based methods, which have high computational requirements, P-TAME offers an efficient alternative by generating high-resolution explanations in a single forward pass during inference. We apply P-TAME to explain the decisions of VGG-16, ResNet-50, and ViT-B-16, three distinct and widely used image classifiers. Quantitative and qualitative results show that P-TAME matches or outperforms previous explainability methods, including model-specific ones.","PeriodicalId":73300,"journal":{"name":"IEEE open journal of signal processing","volume":"6 ","pages":"536-545"},"PeriodicalIF":2.9,"publicationDate":"2025-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10994422","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144171031","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-25DOI: 10.1109/OJSP.2025.3545337
Manjun Cui;Zhichao Zhang;Jie Han;Yunjie Chen;Chunzheng Cao
The convolution type of the Cohen's class time-frequency distribution (CCTFD) is a useful and effective time-frequency analysis tool for additive noises jamming signals. However, it can't meet the requirement of high-performance denoising under low signal-to-noise ratio conditions. In this paper, we define the generalized metaplectic convolution-based Cohen's class time-frequency distribution (GMC-CCTFD) by replacing the traditional convolution operator in CCTFD with the generalized convolution operator of metaplectic transform (MT). This new definition leverages the high degrees of freedom and flexibility of MT, improving performance in non-stationary signal analysis. We then establish a fundamental theory about the GMC-CCTFD's essential properties. By integrating the Wiener filter principle with the time-frequency filtering mechanism of GMC-CCTFD, we design a least-squares adaptive filter in the Wigner distribution-MT domain. This allows us to achieve adaptive filtering denoising based on GMC-CCTFD, giving birth to the least-squares adaptive filter-based GMC-CCTFD. Furthermore, we conduct several examples and apply the proposed filtering method to real-world datasets, demonstrating its superior performance in noise suppression compared to some state-of-the-art methods.
{"title":"Generalized Metaplectic Convolution-Based Cohen's Class Time-Frequency Distribution: Theory and Application","authors":"Manjun Cui;Zhichao Zhang;Jie Han;Yunjie Chen;Chunzheng Cao","doi":"10.1109/OJSP.2025.3545337","DOIUrl":"https://doi.org/10.1109/OJSP.2025.3545337","url":null,"abstract":"The convolution type of the Cohen's class time-frequency distribution (CCTFD) is a useful and effective time-frequency analysis tool for additive noises jamming signals. However, it can't meet the requirement of high-performance denoising under low signal-to-noise ratio conditions. In this paper, we define the generalized metaplectic convolution-based Cohen's class time-frequency distribution (GMC-CCTFD) by replacing the traditional convolution operator in CCTFD with the generalized convolution operator of metaplectic transform (MT). This new definition leverages the high degrees of freedom and flexibility of MT, improving performance in non-stationary signal analysis. We then establish a fundamental theory about the GMC-CCTFD's essential properties. By integrating the Wiener filter principle with the time-frequency filtering mechanism of GMC-CCTFD, we design a least-squares adaptive filter in the Wigner distribution-MT domain. This allows us to achieve adaptive filtering denoising based on GMC-CCTFD, giving birth to the least-squares adaptive filter-based GMC-CCTFD. Furthermore, we conduct several examples and apply the proposed filtering method to real-world datasets, demonstrating its superior performance in noise suppression compared to some state-of-the-art methods.","PeriodicalId":73300,"journal":{"name":"IEEE open journal of signal processing","volume":"6 ","pages":"348-368"},"PeriodicalIF":2.9,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10902015","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143628714","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Image segmentation is an essential initial stage in several computer vision applications. However, unsupervised image segmentation is still a challenging task in some cases such as when objects with a similar visual appearance overlap. Unlike 2D images, 4D Light Fields (LFs) convey both spatial and angular scene information facilitating depth/disparity estimation, which can be further used to guide the segmentation. Existing 4D LF segmentation methods that target object level (i.e., mid-level and high-level) segmentation are typically semi-supervised or supervised with ground truth labels and mostly support only densely sampled 4D LFs. This paper proposes a novel unsupervised mid-level 4D LF Segmentation method using Graph Neural Networks (LFSGNN), which segments all LF views consistently. To achieve that, the 4D LF is represented as a hypergraph, whose hypernodes are obtained based on hyperpixel over-segmentation. Then, a graph neural network is used to extract deep features from the LF and assign segmentation labels to all hypernodes. Afterwards, the network parameters are updated iteratively to achieve better object separation using backpropagation. The proposed segmentation method supports both densely and sparsely sampled 4D LFs. Experimental results on synthetic and real 4D LF datasets show that the proposed method outperforms benchmark methods both in terms of segmentation spatial accuracy and angular consistency.
{"title":"Unsupervised Angularly Consistent 4D Light Field Segmentation Using Hyperpixels and a Graph Neural Network","authors":"Maryam Hamad;Caroline Conti;Paulo Nunes;Luís Ducla Soares","doi":"10.1109/OJSP.2025.3545356","DOIUrl":"https://doi.org/10.1109/OJSP.2025.3545356","url":null,"abstract":"Image segmentation is an essential initial stage in several computer vision applications. However, unsupervised image segmentation is still a challenging task in some cases such as when objects with a similar visual appearance overlap. Unlike 2D images, 4D Light Fields (LFs) convey both spatial and angular scene information facilitating depth/disparity estimation, which can be further used to guide the segmentation. Existing 4D LF segmentation methods that target object level (i.e., mid-level and high-level) segmentation are typically semi-supervised or supervised with ground truth labels and mostly support only densely sampled 4D LFs. This paper proposes a novel unsupervised mid-level 4D LF Segmentation method using Graph Neural Networks (LFSGNN), which segments all LF views consistently. To achieve that, the 4D LF is represented as a hypergraph, whose hypernodes are obtained based on hyperpixel over-segmentation. Then, a graph neural network is used to extract deep features from the LF and assign segmentation labels to all hypernodes. Afterwards, the network parameters are updated iteratively to achieve better object separation using backpropagation. The proposed segmentation method supports both densely and sparsely sampled 4D LFs. Experimental results on synthetic and real 4D LF datasets show that the proposed method outperforms benchmark methods both in terms of segmentation spatial accuracy and angular consistency.","PeriodicalId":73300,"journal":{"name":"IEEE open journal of signal processing","volume":"6 ","pages":"333-347"},"PeriodicalIF":2.9,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10902629","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143629648","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-24DOI: 10.1109/OJSP.2025.3545379
Saeed Ghoorchian;Steven Bilaj;Setareh Maghsudi
Sequential decision-making under uncertainty is often associated with long feedback delays. Such delays degrade the performance of the learning agent in identifying a subset of arms with the optimal collective reward in the long run. This problem becomes significantly challenging in a non-stationary environment with structural dependencies amongst the reward distributions associated with the arms. Therefore, besides adapting to delays and environmental changes, learning the causal relations alleviates the adverse effects of feedback delay on the decision-making process. We formalize the described setting as a non-stationary and delayed combinatorial semi-bandit problem with causally related rewards. We model the causal relations by a directed graph in a stationary structural equation model. The agent maximizes the long-term average payoff, defined as a linear function of the base arms' rewards. We develop a policy that learns the structural dependencies from delayed feedback and utilizes that to optimize the decision-making while adapting to drifts. We prove a regret bound for the performance of the proposed algorithm. Besides, we evaluate our method via numerical analysis using synthetic and real-world datasets to detect the regions that contribute the most to the spread of Covid-19 in Italy.
{"title":"Non-Stationary Delayed Combinatorial Semi-Bandit With Causally Related Rewards","authors":"Saeed Ghoorchian;Steven Bilaj;Setareh Maghsudi","doi":"10.1109/OJSP.2025.3545379","DOIUrl":"https://doi.org/10.1109/OJSP.2025.3545379","url":null,"abstract":"Sequential decision-making under uncertainty is often associated with long feedback delays. Such delays degrade the performance of the learning agent in identifying a subset of arms with the optimal collective reward in the long run. This problem becomes significantly challenging in a non-stationary environment with structural dependencies amongst the reward distributions associated with the arms. Therefore, besides adapting to delays and environmental changes, learning the causal relations alleviates the adverse effects of feedback delay on the decision-making process. We formalize the described setting as a non-stationary and delayed combinatorial semi-bandit problem with causally related rewards. We model the causal relations by a directed graph in a stationary structural equation model. The agent maximizes the long-term average payoff, defined as a linear function of the base arms' rewards. We develop a policy that learns the structural dependencies from delayed feedback and utilizes that to optimize the decision-making while adapting to drifts. We prove a regret bound for the performance of the proposed algorithm. Besides, we evaluate our method via numerical analysis using synthetic and real-world datasets to detect the regions that contribute the most to the spread of Covid-19 in Italy.","PeriodicalId":73300,"journal":{"name":"IEEE open journal of signal processing","volume":"6 ","pages":"369-384"},"PeriodicalIF":2.9,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10902019","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143627851","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：