arXiv subjects

Moncef Gabbouj

Publications and source records attributed to Moncef Gabbouj.

At least 19 recordsLinked to original sources

arXiv2026

Multi-Pass, Multi-View Blended Learning for High-Fidelity Volumetric CT Synthesis from Chest X-Rays

Reconstructing volumetric Computed Tomography (CT) from a single 2D chest radiograph (CXR) is an ill-posed inverse problem, further complicated by the scarcity of paired CXR-CT training data. Prior approaches address this by training on Digitally Reconstructed Radiographs (DRRs), which are synthetic projections derived from CT volumes. However, the domain gap between DRRs and real CXRs limits generalization, often resulting in coarse or anatomically inconsistent reconstructions when applied to clinical images. To address this challenging problem, this study introduces a Multi-Pass Multi-View Blended Learning framework for synthesizing high-fidelity volumetric CT directly from real chest X-ray (CXR) images. The proposed approach progressively decomposes the synthesis task into two distinct, complementary learning stages. Stage 1 is an unsupervised CXR-to-DRR Domain Adaptation, while Stage 2 includes three passes, namely, (a) supervised DRR-to-CT Transformation, (b) unsupervised Multi-View Slice Refinement, followed by (c) Progressive Transfer Learning (PTL). With such a blended learning paradigm, the proposed approach mitigates the synthetic-to-real domain gap while enhancing both the structural integrity and anatomical detail of the final output. On the LIDC-IDRI dataset, where paired DRR-CT ground truth is available for quantitative evaluation, the proposed method improves upon prior methods by up to 14% in PSNR and 7.6% in SSIM. The framework successfully generates structurally consistent and anatomically realistic high-fidelity CT volumes from real CXRs, marking a significant advancement toward clinical viability of CT reconstruction from standard radiographic images.

cs.LG↗

arXiv2026

From Reports to Ontologies: Ontology-Guided Representation Learning for 12-Lead ECG

The 12-lead electrocardiogram (ECG) is a quasi-periodic, multi-channel signal with diagnostic content spanning timescales from millisecond waveform morphology to multi-second rhythm dynamics. Existing ECG representation learning relies on signal-only self-supervision or ECG-text multimodal alignment, neither of which exploits the structured diagnostic codes attached to every clinical recording. We present \textbf{MAR-ECG}, an ontology-guided masked autoregressive framework that supervises the encoder with a curated 40-node SNOMED-CT cardiac graph through \emph{graph alignment}, eliminating the need for paired clinical reports. MAR-ECG combines two complementary objectives. First, \emph{graph-smoothed contrastive learning} (GSCL) anchors the encoder's rhythm-pooled features to the SNOMED graph, softening supervision targets by ontology distance so that clinically related concepts reinforce one another rather than function as hard negatives. Second, \emph{multi-scale physiological supervision} complements GSCL with signal-derived patch auxiliaries that target rhythm-physiology statistics extracted automatically from the input, extending supervision beyond the patch tier at no annotation cost. Pretrained on ${\sim}40$K publicly available 12-lead ECGs with SNOMED-CT codes and evaluated by frozen linear probing on five downstream classification benchmarks, MAR-ECG consistently outperforms a strong masked-autoregressive baseline, with mean gains in the low-label regime. Despite the absence of paired clinical text, MAR-ECG achieves performance competitive with state-of-the-art multimodal ECG-text methods.

cs.CE↗

arXiv2026

Axiomatizing Neural Networks via Pursuit of Subspaces

While deep neural networks have achieved remarkable success across a wide range of domains, their underlying mechanisms remain poorly understood, and they are often regarded as black boxes. This gap between empirical performance and theoretical understanding poses a challenge analogous to the pre-axiomatic stage of classical geometry. In this work, we introduce the Pursuit of Subspaces (PoS) hypothesis, an axiomatic framework that formulates neural network behavior through a set of geometric postulates. These axioms, together with their derived consequences, provide a unified perspective on representation, computation, and generalization in both shallow and deep architectures. We show that this framework yields geometric explanations for fundamental questions in deep learning, including representation structure, architectural mechanisms, and generalization behavior, offering a principled step toward a coherent theoretical foundation.

cs.LG↗

arXiv2026

The Eleventh NTIRE 2026 Efficient Super-Resolution Challenge Report

This paper reviews the NTIRE 2026 challenge on efficient single-image super-resolution with a focus on the proposed solutions and results. The aim of this challenge is to devise a network that reduces one or several aspects, such as runtime, parameters, and FLOPs, while maintaining PSNR of around 26.90 dB on the DIV2K_LSDIR_valid dataset, and 26.99 dB on the DIV2K_LSDIR_test dataset. The challenge had 95 registered participants, and 15 teams made valid submissions. They gauge the state-of-the-art results for efficient single-image super-resolution.

cs.CV↗

arXiv2026

MTS-CSNet: Multiscale Tensor Factorization for Deep Compressive Sensing on RGB Images

Deep learning based compressive sensing (CS) methods typically learn sampling operators using convolutional or block wise fully connected layers, which limit receptive fields and scale poorly for high dimensional data. We propose MTSCSNet, a CS framework based on Multiscale Tensor Summation (MTS) factorization, a structured operator for efficient multidimensional signal processing. MTS performs mode-wise linear transformations with multiscale summation, enabling large receptive fields and effective modeling of cross-dimensional correlations. In MTSCSNet, MTS is first used as a learnable CS operator that performs linear dimensionality reduction in tensor space, with its adjoint defining the initial back-projection, and is then applied in the reconstruction stage to directly refine this estimate. This results in a simple feed-forward architecture without iterative or proximal optimization, while remaining parameter and computation efficient. Experiments on standard CS benchmarks show that MTSCSNet achieves state-of-the-art reconstruction performance on RGB images, with notable PSNR gains and faster inference, even compared to recent diffusion-based CS methods, while using a significantly more compact feed-forward architecture.

eess.IV↗

arXiv2025

Blind Quality Enhancement of Compressed Video via Fine-Grained Degradation-Guided Sequential Inference

Existing studies on quality enhancement for compressed video (QECV) predominantly rely on known quantization parameters (QPs), training separate enhancement models for each QP setting, which are referred to as non-blind methods. However, in practical scenarios such as transcoding and transmission, QPs may be partially or entirely unavailable, which limits the applicability of these methods and motivates the development of blind QECV techniques. Existing blind methods typically generate degradation vectors using classification models trained with cross-entropy loss, and employ them as channel attention to guide artifact reduction. Nevertheless, such degradation representations mainly capture global compression information and lack fine-grained spatial cues, making them less effective in handling spatially varying artifact patterns. To address this issue, we propose a pre-trained degradation representation learning module that decouples and extracts high-dimensional, multi-scale degradation representations from compressed video content, providing fine-grained guidance for artifact reduction. Furthermore, most existing blind and nonblind methods adopt a uniform inference architecture for all compression levels, ignoring the distinct computational demands of different QPs. To overcome this limitation, we introduce a sequential inference strategy that adaptively adjusts the number of artifact reduction stages according to the estimated compression level. Extensive experiments show that the proposed method significantly improves enhancement performance. In particular, at QP = 22, it raises PSNR improvement from 0.31 dB to 0.65 dB over the previous state-of-the-art blind method. Meanwhile, with the proposed sequential inference strategy, the average inference time at QP = 22 is reduced by 50% compared with that at QP = 42.

cs.CV↗

arXiv2025

DRACO: Data Replication and Collection Framework for Enhanced Data Availability and Robustness in IoT Networks

The Internet of Things (IoT) bridges the gap between the physical and digital worlds, enabling seamless interaction with real-world objects via the Internet. However, IoT systems face significant challenges in ensuring efficient data generation, collection, and management, particularly due to the resource-constrained and unreliable nature of connected devices, which can lead to data loss. This paper presents DRACO (Data Replication and Collection), a framework that integrates a distributed hop-by-hop data replication approach with an overhead-free mobile sink-based data collection strategy. DRACO enhances data availability, optimizes replica placement, and ensures efficient data retrieval even under node failures and varying network densities. Extensive ns-3 simulations demonstrate that DRACO outperforms state-of-the-art techniques, improving data availability by up to 15% and 34%, and replica creation by up to 18% and 40%, compared to greedy and random replication techniques, respectively. DRACO also ensures efficient data dissemination through optimized replica distribution and achieves superior data collection efficiency under varying node densities and failure scenarios as compared to commonly used uncontrolled sink mobility approaches namely random walk and self-avoiding random walk. By addressing key IoT data management challenges, DRACO offers a scalable and resilient solution well-suited for emerging use cases.

cs.NI↗

arXiv2025

Randomized PCA Forest for Unsupervised Outlier Detection

We propose a novel unsupervised outlier detection method based on Randomized Principal Component Analysis (PCA). Motivated by the performance of Randomized PCA (RPCA) Forest in approximate K-Nearest Neighbor (KNN) search, we develop a novel unsupervised outlier detection method that utilizes RPCA Forest for unsupervised outlier detection by deriving an outlier score from its intrinsic properties. Experimental results showcase the superiority of the proposed approach compared to the classical and state-of-the-art methods in performing the outlier detection task on several datasets while performing competitively on the rest. The extensive analysis of the proposed method reflects its robustness and its computational efficiency, highlighting it as a good choice for unsupervised outlier detection.

cs.LG↗

arXiv2025

UL-DD: A Multimodal Drowsiness Dataset Using Video, Biometric Signals, and Behavioral Data

In this study, we present a comprehensive public dataset for driver drowsiness detection, integrating multimodal signals of facial, behavioral, and biometric indicators. Our dataset includes 3D facial video using a depth camera, IR camera footage, posterior videos, and biometric signals such as heart rate, electrodermal activity, blood oxygen saturation, skin temperature, and accelerometer data. This data set provides grip sensor data from the steering wheel and telemetry data from the American truck simulator game to provide more information about drivers' behavior while they are alert and drowsy. Drowsiness levels were self-reported every four minutes using the Karolinska Sleepiness Scale (KSS). The simulation environment consists of three monitor setups, and the driving condition is completely like a car. Data were collected from 19 subjects (15 M, 4 F) in two conditions: when they were fully alert and when they exhibited signs of sleepiness. Unlike other datasets, our multimodal dataset has a continuous duration of 40 minutes for each data collection session per subject, contributing to a total length of 1,400 minutes, and we recorded gradual changes in the driver state rather than discrete alert/drowsy labels. This study aims to create a comprehensive multimodal dataset of driver drowsiness that captures a wider range of physiological, behavioral, and driving-related signals. The dataset will be available upon request to the corresponding author.

cs.CV↗

arXiv2025

Crucial-Diff: A Unified Diffusion Model for Crucial Image and Annotation Synthesis in Data-scarce Scenarios

The scarcity of data in various scenarios, such as medical, industry and autonomous driving, leads to model overfitting and dataset imbalance, thus hindering effective detection and segmentation performance. Existing studies employ the generative models to synthesize more training samples to mitigate data scarcity. However, these synthetic samples are repetitive or simplistic and fail to provide "crucial information" that targets the downstream model's weaknesses. Additionally, these methods typically require separate training for different objects, leading to computational inefficiencies. To address these issues, we propose Crucial-Diff, a domain-agnostic framework designed to synthesize crucial samples. Our method integrates two key modules. The Scene Agnostic Feature Extractor (SAFE) utilizes a unified feature extractor to capture target information. The Weakness Aware Sample Miner (WASM) generates hard-to-detect samples using feedback from the detection results of downstream model, which is then fused with the output of SAFE module. Together, our Crucial-Diff framework generates diverse, high-quality training data, achieving a pixel-level AP of 83.63% and an F1-MAX of 78.12% on MVTec. On polyp dataset, Crucial-Diff reaches an mIoU of 81.64% and an mDice of 87.69%. Code is publicly available at https://github.com/JJessicaYao/Crucial-diff.

cs.CV↗

arXiv2025

Expert Operational GANS: Towards Real-Color Underwater Image Restoration

The wide range of deformation artifacts that arise from complex light propagation, scattering, and depth-dependent attenuation makes the underwater image restoration to remain a challenging problem. Like other single deep regressor networks, conventional GAN-based restoration methods struggle to perform well across this heterogeneous domain, since a single generator network is typically insufficient to capture the full range of visual degradations. In order to overcome this limitation, we propose xOp-GAN, a novel GAN model with several expert generator networks, each trained solely on a particular subset with a certain image quality. Thus, each generator can learn to maximize its restoration performance for a particular quality range. Once a xOp-GAN is trained, each generator can restore the input image and the best restored image can then be selected by the discriminator based on its perceptual confidence score. As a result, xOP-GAN is the first GAN model with multiple generators where the discriminator is being used during the inference of the regression task. Experimental results on benchmark Large Scale Underwater Image (LSUI) dataset demonstrates that xOp-GAN achieves PSNR levels up to 25.16 dB, surpassing all single-regressor models by a large margin even, with reduced complexity.

cs.CV↗

arXiv2025

Multi-Scale Tensorial Summation and Dimensional Reduction Guided Neural Network for Edge Detection

Edge detection has attracted considerable attention thanks to its exceptional ability to enhance performance in downstream computer vision tasks. In recent years, various deep learning methods have been explored for edge detection tasks resulting in a significant performance improvement compared to conventional computer vision algorithms. In neural networks, edge detection tasks require considerably large receptive fields to provide satisfactory performance. In a typical convolutional operation, such a large receptive field can be achieved by utilizing a significant number of consecutive layers, which yields deep network structures. Recently, a Multi-scale Tensorial Summation (MTS) factorization operator was presented, which can achieve very large receptive fields even from the initial layers. In this paper, we propose a novel MTS Dimensional Reduction (MTS-DR) module guided neural network, MTS-DR-Net, for the edge detection task. The MTS-DR-Net uses MTS layers, and corresponding MTS-DR blocks as a new backbone to remove redundant information initially. Such a dimensional reduction module enables the neural network to focus specifically on relevant information (i.e., necessary subspaces). Finally, a weight U-shaped refinement module follows MTS-DR blocks in the MTS-DR-Net. We conducted extensive experiments on two benchmark edge detection datasets: BSDS500 and BIPEDv2 to verify the effectiveness of our model. The implementation of the proposed MTS-DR-Net can be found at https://github.com/LeiXuAI/MTS-DR-Net.git.

cs.CV↗

arXiv2025

Text-Audio-Visual-conditioned Diffusion Model for Video Saliency Prediction

Video saliency prediction is crucial for downstream applications, such as video compression and human-computer interaction. With the flourishing of multimodal learning, researchers started to explore multimodal video saliency prediction, including audio-visual and text-visual approaches. Auditory cues guide the gaze of viewers to sound sources, while textual cues provide semantic guidance for understanding video content. Integrating these complementary cues can improve the accuracy of saliency prediction. Therefore, we attempt to simultaneously analyze visual, auditory, and textual modalities in this paper, and propose TAVDiff, a Text-Audio-Visual-conditioned Diffusion Model for video saliency prediction. TAVDiff treats video saliency prediction as an image generation task conditioned on textual, audio, and visual inputs, and predicts saliency maps through stepwise denoising. To effectively utilize text, a large multimodal model is used to generate textual descriptions for video frames and introduce a saliency-oriented image-text response (SITR) mechanism to generate image-text response maps. It is used as conditional information to guide the model to localize the visual regions that are semantically related to the textual description. Regarding the auditory modality, it is used as another conditional information for directing the model to focus on salient regions indicated by sounds. At the same time, since the diffusion transformer (DiT) directly concatenates the conditional information with the timestep, which may affect the estimation of the noise level. To achieve effective conditional guidance, we propose Saliency-DiT, which decouples the conditional information from the timestep. Experimental results show that TAVDiff outperforms existing methods, improving 1.03\%, 2.35\%, 2.71\% and 0.33\% on SIM, CC, NSS and AUC-J metrics, respectively.

cs.CV↗

arXiv2025

Multiscale Tensor Summation Factorization as a New Neural Network Layer (MTS Layer) for Multidimensional Data Processing

Multilayer perceptrons (MLP), or fully connected artificial neural networks, are known for performing vector-matrix multiplications using learnable weight matrices; however, their practical application in many machine learning tasks, especially in computer vision, can be limited due to the high dimensionality of input-output pairs at each layer. To improve efficiency, convolutional operators have been utilized to facilitate weight sharing and local connections, yet they are constrained by limited receptive fields. In this paper, we introduce Multiscale Tensor Summation (MTS) Factorization, a novel neural network operator that implements tensor summation at multiple scales, where each tensor to be summed is obtained through Tucker-decomposition-like mode products. Unlike other tensor decomposition methods in the literature, MTS is not introduced as a network compression tool; instead, as a new backbone neural layer. MTS not only reduces the number of parameters required while enhancing the efficiency of weight optimization compared to traditional dense layers (i.e., unfactorized weight matrices in MLP layers), but it also demonstrates clear advantages over convolutional layers. The proof-of-concept experimental comparison of the proposed MTS networks with MLPs and Convolutional Neural Networks (CNNs) demonstrates their effectiveness across various tasks, such as classification, compression, and signal restoration. Additionally, when integrated with modern non-linear units such as the multi-head gate (MHG), also introduced in this study, the corresponding neural network, MTSNet, demonstrates a more favorable complexity-performance tradeoff compared to state-of-the-art transformers in various computer vision applications. The software implementation of the MTS layer and the corresponding MTS-based networks, MTSNets, is shared at https://github.com/mehmetyamac/MTSNet.

cs.LG↗

arXiv2025

DVLTA-VQA: Decoupled Vision-Language Modeling with Text-Guided Adaptation for Blind Video Quality Assessment

Inspired by the dual-stream theory of the human visual system (HVS) - where the ventral stream is responsible for object recognition and detail analysis, while the dorsal stream focuses on spatial relationships and motion perception - an increasing number of video quality assessment (VQA) works built upon this framework are proposed. Recent advancements in large multi-modal models, notably Contrastive Language-Image Pretraining (CLIP), have motivated researchers to incorporate CLIP into dual-stream-based VQA methods. This integration aims to harness the model's superior semantic understanding capabilities to replicate the object recognition and detail analysis in ventral stream, as well as spatial relationship analysis in dorsal stream. However, CLIP is originally designed for images and lacks the ability to capture temporal and motion information inherent in videos. To address the limitation, this paper propose a Decoupled Vision-Language Modeling with Text-Guided Adaptation for Blind Video Quality Assessment (DVLTA-VQA), which decouples CLIP's visual and textual components, and integrates them into different stages of the NR-VQA pipeline. Specifically, a Video-Based Temporal CLIP module is proposed to explicitly model temporal dynamics and enhance motion perception, aligning with the dorsal stream. Additionally, a Temporal Context Module is developed to refine inter-frame dependencies, further improving motion modeling. On the ventral stream side, a Basic Visual Feature Extraction Module is employed to strengthen detail analysis. Finally, a text-guided adaptive fusion strategy is proposed to enable dynamic weighting of features, facilitating more effective integration of spatial and temporal information.

cs.CV↗

arXiv2025

Progressive Transfer Learning for Multi-Pass Fundus Image Restoration

Diabetic retinopathy is a leading cause of vision impairment, making its early diagnosis through fundus imaging critical for effective treatment planning. However, the presence of poor quality fundus images caused by factors such as inadequate illumination, noise, blurring and other motion artifacts yields a significant challenge for accurate DR screening. In this study, we propose progressive transfer learning for multi pass restoration to iteratively enhance the quality of degraded fundus images, ensuring more reliable DR screening. Unlike previous methods that often focus on a single pass restoration, multi pass restoration via PTL can achieve a superior blind restoration performance that can even improve most of the good quality fundus images in the dataset. Initially, a Cycle GAN model is trained to restore low quality images, followed by PTL induced restoration passes over the latest restored outputs to improve overall quality in each pass. The proposed method can learn blind restoration without requiring any paired data while surpassing its limitations by leveraging progressive learning and fine tuning strategies to minimize distortions and preserve critical retinal features. To evaluate PTL's effectiveness on multi pass restoration, we conducted experiments on DeepDRiD, a large scale fundus imaging dataset specifically curated for diabetic retinopathy detection. Our result demonstrates state of the art performance, showcasing PTL's potential as a superior approach to iterative image quality restoration.

eess.IV↗

arXiv2025

FANeRV: Frequency Separation and Augmentation based Neural Representation for Video

Neural representations for video (NeRV) have gained considerable attention for their strong performance across various video tasks. However, existing NeRV methods often struggle to capture fine spatial details, resulting in vague reconstructions. In this paper, we present a Frequency Separation and Augmentation based Neural Representation for video (FANeRV), which addresses these limitations with its core Wavelet Frequency Upgrade Block. This block explicitly separates input frames into high and low-frequency components using discrete wavelet transform, followed by targeted enhancement using specialized modules. Finally, a specially designed gated network effectively fuses these frequency components for optimal reconstruction. Additionally, convolutional residual enhancement blocks are integrated into the later stages of the network to balance parameter distribution and improve the restoration of high-frequency details. Experimental results demonstrate that FANeRV significantly improves reconstruction performance and excels in multiple tasks, including video compression, inpainting, and interpolation, outperforming existing NeRV methods.

cs.CV↗

arXiv2025

Dual-Domain Fusion for Semi-Supervised Learning

Labeled time-series data is often expensive and difficult to obtain, making it challenging to train accurate machine learning models for real-world applications such as anomaly detection or fault diagnosis. The scarcity of labeled samples limits model generalization and leaves valuable unlabeled data underutilized. We propose Dual-Domain Fusion (DDF), a new model-agnostic semi-supervised learning (SSL) framework applicable to any time-series signal. DDF performs dual-domain training by combining the one-dimensional time-domain signals with their two-dimensional time-frequency representations and fusing them to maximize learning performance. Its tri-model architecture consists of time-domain, time-frequency, and fusion components, enabling the model to exploit complementary information across domains during training. To support practical deployment, DDF maintains the same inference cost as standard time-domain models by discarding the time-frequency and fusion branches at test time. Experimental results on two public fault diagnosis datasets demonstrate substantial accuracy improvements of 8-46% over widely used SSL methods FixMatch, MixMatch, Mean Teacher, Adversarial Training, and Self-training. These results show that DDF provides an effective and generalizable strategy for semi-supervised time-series classification.

cs.LG↗