CNN
-
Readout and Operating-Point Sensitivity in Event-Stream Candidate Selection
Abstract
Event-triggered recording needs a useful combination of target capture and false triggers, yet representation comparisons can change with readout and threshold calibration. We evaluate real event accumulations from 520 DailyDVS-200 clips and 47 participants using participant-disjoint training, validation, and testing. The original study varies frozen encoder scale, accumulation duration, and temporal view count; a post-review extension adds two supervised-pretrained convolutional encoders, a 61,586-parameter trained CNN with three seeds, ten repeated participant partitions, and calibration sensitivity. At 50 ms/eight views under the primary handshake-or-fall policy, DINO-S CLS captures 101/132 targets with 40/388 false triggers, versus 78/132 and 35/388 for patch mean. DINO-B CLS has lower selected-threshold capture but higher fold-wise low-FPR partial AUC (0.746 versus 0.732). MobileNetV3-Small captures 97/132 with 53/388 false triggers, demonstrating why lightweight baselines and actual operating points matter. Across ten dependent repartitions, mean normalized partial AUC is 0.738 for DINO-B CLS and 0.674 for MobileNet. The original LeJEPA S-to-B capture difference is 8.3 points, but its multiplicity-adjusted interval includes zero. Duration and view-count effects remain policy dependent. We find no established JEPA-specific advantage. The evidence concerns offline action-defined candidate selection on previously used development data; it does not establish personal recording value, continuous false alarms per hour, or eyewear energy.
Abstract (translated)
URL
https://arxiv.org/abs/2610.36743
PDF
-
Detecting and Mitigating Query-Based System Prompt Leakage Attacks
2026-10-26 21:23:10Tushar Nayan, Pratik Poudel, Qian Lou, Yuede Ji, Jason Liu, Ruimin SunAbstract
Large Language Models (LLMs) rely on proprietary system prompts to enforce task directives, safety policies, and access controls. These prompts are vulnerable to query-based leakage attacks, where black-box adversaries extract confidential instructions through adaptive, multi-turn interactions. Existing defenses often assess queries independently, missing malicious behavior that emerges across interactions. We present AdvGuard, a model-agnostic framework for detecting and mitigating system prompt leakage. AdvGuard models cross-query relationships using a bounded semantic interaction graph, statistically filters candidate components, and converts them into line graphs for graph convolutional network (GCN) classification. This approach captures multi-hop patterns in query similarity that distinguish coordinated extraction from benign workflows. A lightweight prompt-level detector provides protection before sufficient interaction history accumulates, and the framework supports black-box LLM deployments. In mixed-query evaluations, AdvGuard improves recall by up to 36% over the strongest baseline while maintaining a false positive rate of at most 3.4%. In multi-turn workloads, it achieves 97.23%-99.1% F1 with 100% recall. Leave-one-attack-family-out tests yield 99.98% mean recall and 99.99% mean F1, with no observed false positives. Integrated into the adaptive PLeak and LeakAgent attack loops, AdvGuard limits exact-match leakage to 0.00-0.01 and substring-match leakage to 0.01-0.09 across evaluated victim models. These results demonstrate robust detection of unseen attack families and substantially reduced prompt reconstruction.
Abstract (translated)
URL
https://arxiv.org/abs/2610.36295
PDF
-
AdaTrendLike: Adaptive Hierarchical Detrending and Trend Likelihood Scoring for Time Series Anomaly Detection
2026-10-26 13:14:23Van Kwan Zhi Koh, Songnan Lin, Rongmo Luo, Zhiping Lin, Bihan WenAbstract
The rapid proliferation of Industrial Internet of Things devices has led to increasingly large-scale and non-stationary time-series data, posing significant challenges for time-series anomaly detection (TSAD). Existing approaches often focus on reconstructing or forecasting observations while overlooking the role of trend dynamics, which constitute a major source of non-stationarity and contain valuable information for anomaly identification. To address this limitation, we propose AdaTrendLike, a TSAD framework that directly estimates trend likelihoods for anomaly detection. Specifically, we introduce Standardization Embedding to capture local statistical characteristics as latent representations and AdaDetrending to adaptively decompose input series into trend and detrended components. The detrended component is processed through a Fast Fourier Transform and a complex-valued convolutional neural network to learn normal periodic patterns, while TrendEst models the distribution of the trend component. Based on the estimated distribution, TrendLike computes anomaly scores by measuring the likelihood of observed trends, enabling effective detection of deviations from normal behavior. In addition to improving detection performance, the proposed framework provides feature-level interpretability by identifying anomalies through deviations in the estimated trend distribution. Extensive experiments on five public benchmark datasets demonstrate that AdaTrendLike consistently outperforms state-of-the-art TSAD methods, validating its effectiveness and robustness across diverse application scenarios.
Abstract (translated)
URL
https://arxiv.org/abs/2610.35400
PDF
-
Toward Clinical Translation of Deep Learning-Based Intracranial Super-Resolution 4D Flow MRI Using Multi-Cohort Transfer Learning
2026-10-26 13:11:18Oliver Welin Odeback, Susanne Schnell, Patrick Winter, Johan Lundberg, Fredrik Piehl, Tobias Granberg, Alexander Fyrdahl, David MarleviAbstract
We evaluated synthetic pretraining and multi-cohort transfer learning for deep learning-based super-resolution of intracranial 4D Flow MRI across heterogeneous neurologic cohorts. This mixed prospective-retrospective study analyzed 18 participants (12 healthy participants, 3 with moyamoya disease, and 3 with multiple sclerosis) with paired 1.2-mm and 0.6-mm 4D Flow MRI scans. A convolutional neural network pretrained on synthetic cerebrovascular data was fine-tuned using cohort-specific or pooled multi-cohort in vivo data. High-resolution-derived inputs enabled voxel-wise evaluation; native standard-resolution scans were used for angiographic and hemodynamic analyses. Synthetic pretraining reduced mean artery-wise velocity-normalized root mean square error (vNRMSE) versus interpolation (0.147 vs 0.166). Pooled transfer learning yielded the lowest mean vNRMSE (0.119 vs 0.127 for cohort-specific models and 0.147 for synthetic pretraining), with narrower 95% limits-of-agreement widths than synthetic pretraining across all test cases (0.109-0.222 vs 0.154-0.278 m/s). Super-resolved phase-contrast angiography achieved higher precision-recall area under the curve than native standard-resolution imaging in all cohorts (0.848-0.896 vs 0.486-0.805). These results indicate that pooled transfer learning improves cross-cohort reconstruction agreement and that super-resolution can improve vessel depiction, supporting further multi-center validation for cerebrovascular imaging.
Abstract (translated)
URL
https://arxiv.org/abs/2610.35396
PDF
-
ACSAN: All-Convolutional Self-Attention Network Integrating Convolutional Operations with Vision Transformer
2026-10-26 12:58:25Zimian Wei, Tianqi Zhang, Hengyue PanAbstract
In the past few years, Vision Transformer (ViT) has achieved excellent performance in the field of computer vision. However, there still some problems remain. For instance, ViTs heavily rely on large-scale training data since they simply contain a large number of trainable parameters, which slows down their learning efficiency and limits their applicability in resource-constrained scenarios. In this paper, we propose a novel deep learning model, namely All-Convolutional Self-Attention Network (ACSAN), which applies convolution operations to replace fully-connected matrices multiplications in the ViT framework. To implement ACSAN, we firstly design Dynamic Convolutional Self-Attention (DCSA) as the basic module, which employs multi-scale dilated convolutions to generate Query, Key, and Value. We defined spatial self-attention and channel self-attention to generate attention features respectively. The two attention features are finally merged as the output of the DCSA module. Based on DCSA, we then construct the basic ACSAN block. Comparing with ViT, we use DCSA to replace the regular self-attention operations, and use convolution layers to replace MLPs. To evaluate the performance of the proposed method, we train ACSAN on three widely-used image classification databases, i.e. CIFAR-10, CIFAR-100 and ImageNet-1k, from scratch. Experimental results show that ACSAN achieves excellent classification accuracy comparing with standard ViT with comparable or fewer parameters, as well as other state-of-the-art methods. Ablation studies verify that each component contributes positively to the final performance.
Abstract (translated)
URL
https://arxiv.org/abs/2610.35375
PDF
-
Kronecker-Structured Video Completion with Cross-Fitted Self-Supervised Residual Learning
2026-10-26 09:12:45Qi Qi, Yanfei Wang, Yanjun Cui, Jun-e FengAbstract
Tube-wise video completion reconstructs temporal trajectories at spatial locations unobserved in every frame. We propose a two-stage framework combining regularized masked Kronecker product decomposition (KPD) with cross-fitted self-supervised residual learning. First, we estimate a compact structural backbone directly from observed entries using cyclic component-wise least-squares updates, spatial and temporal factor regularization, and regularizer-optimal scale balancing. The exact updates yield a nonincreasing objective. Second, we address the mismatch between in-sample fitting errors and the prediction errors encountered at missing tubes. We partition observed tubes into folds and construct residual targets using backbone models fitted without the corresponding target tubes. A lightweight 3-D convolutional neural network then predicts corrections from the backbone, visible residual context, observation mask, and local detail features. Exact data consistency preserves observed measurements. Experiments include ablations, sensitivity analysis, grayscale and RGB video completion, and structured missing patterns. Our method achieves the highest mean PSNR and SSIM at the higher tested sampling rates on the grayscale benchmark. On eight selected DAVIS RGB sequences, it achieves the highest mean missing-region PSNR and full-frame SSIM and the lowest mean missing-tube temporal-gradient MAE at every evaluated sampling rate.
Abstract (translated)
URL
https://arxiv.org/abs/2610.35065
PDF
-
Shifted Window Temporal Transformer for YOLO-Guided Phase Recognition in Laparoscopic Cholecystectomy Surgery
2026-10-26 08:17:01Sheekar Banerjee, Md. Shahabuddin, Md. Mahbub Hasan Akash, Nabilah, Mohammad Arafat HussainAbstract
Intelligent operating rooms require accurate awareness of surgical workflow for better intra-operative decisions, teamwork, and surgical documentation. Therefore, accurately recognizing surgical phase during surgery is crucial. However, previous artificial intelligence-based methods provide fluctuating predictions for the transitions, restricting their clinical use. To address this challenge, we propose a clinically meaningful framework that integrates a Swin Transformer and Temporal Transformer Encoder (TTE) for effective surgical phase recognition and a parallel YOLOv11s network for real-time surgical instrument localization. To avoid phase flickering and to produce stable workflow predictions, a causal temporal smoothing is applied. The proposed framework is tested on the Cholec80 dataset for the simultaneous recognition of the surgical phases and instruments. The overall phase recognition accuracy of this model was 92%, and the macro average F1-score was 0.86. This performance surpasses CNN based methods such as EndoNet (81.7%) and SV-RCNet (85.3%), as well as temporal convolutional and transformer-based approaches including TeCNO (88.6%), Trans-SVNet (90.9%), and LoViT (91.5%). Besides, the module of instrument detection achieved mAP@0.5 = 0.863. The reliability of the results is confirmed, obtaining a high recognition rate of the workflows, and a high accuracy of the localization of the instruments. The proposed framework can serve as a foundation for intelligent surgical assistance, enriching situation awareness, and potential robotic surgery applications. Code will be made publicly available at: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2610.35005
PDF
-
A Hierarchical Method for Environmental Sounds Recognition in Complex Acoustic Scenes
2026-10-26 06:58:45Zhouwen Li, Haijun Lin, Bowen Lv, Yupeng ChenAbstract
Environmental noise identification is essential for noise control, yet conventional single-stage classifiers suffer from class confusion under imbalanced multiclass conditions. This paper proposes a lightweight hierarchical model integrating a Frequency-Time Adaptive Network (FTANet) with a two-stage classification mechanism. FTANet employs parallel asymmetric one-dimensional convolutions to capture temporal dynamics and frequency-band distributions, while adaptive fusion attention (AFA) enhances discriminative acoustic features. In the first stage, FTANet classifies sounds into five coarse-grained categories covering 25 fine-grained classes. In the second stage, samples are routed to the corresponding category-specific classifiers for fine-grained recognition. On a self-constructed dataset, FTANet achieves 95.45% coarse-grained accuracy with only 0.2004M parameters. On UrbanSound8K, it achieves 79.24% mean accuracy and 80.37% mean F1-score in ten-fold evaluation, outperforming compared convolutional models. Field tests on the Tianjin Online Acoustic Environment Monitoring Platform yield 87.94% coarse-grained accuracy and 97.21% conditional fine-grained accuracy for natural sounds correctly routed to C2. The complete hierarchical model achieves 87.18% overall accuracy and 87.40% weighted-average F1-score, demonstrating its feasibility for urban environmental noise monitoring.
Abstract (translated)
URL
https://arxiv.org/abs/2610.34931
PDF
-
Text Is the Bottleneck: A Small-Scale Replication of LLM Game Playing in Riichi Mahjong
Abstract
We replicate the riichi-mahjong track of "Can Large Language Models Master Complex Card Games?" (arXiv:2509.01328) under a drastically smaller budget: models of at most 2B parameters, one 16 GB consumer GPU, about five GPU-days. (1) With matched data and labels, text is the bottleneck: on the same 100k-decision training set, a 2.6M-parameter convolutional board encoder agrees with the strong AI Mortal on 80.6% of test decisions, above every text-prompt LLM we train (best 77.8%), and places better at the table (2.85 over 1,000 games vs. ~3.0 for the LLMs; paired difference at n=100 not significant). Scaled to 1.71M decisions, a 4.9M-parameter Transformer reaches 94.7% agreement, beats the 0.8B LLMs on identical seeds (-0.45 ranks, sign test p=0.005), and is statistically equivalent to parity against three Mortal champions (TOST within 0.10 ranks, p=6e-4); parity against a teacher-opponent is roughly the ceiling of pure imitation. (2) Training toward the teacher raises teacher agreement more than a 2.5x parameter increase does (+2.5 vs. +1.5 points); on human-record agreement both effects are +1.0, and neither is visible at the table. (3) Few-point agreement differences do not resolve into playing strength within a family: +2.5 agreement points coincide with a paired placement difference of +0.02 +/- 0.12 ranks (p=1.0), and +2.0 points at 2B with -0.06 (p=0.37) - both below the ~0.25-rank resolution of 100 paired games. We also document a paper-code mismatch in the original winner filter, reconstruct its two private engine patches, and show that a divide-and-conquer pipeline makes template-generated Japanese rationales 93% sentence-exact (43% without facts). Per Tenhou's terms we release no trained weights - only code, configurations, and evaluation protocols.
Abstract (translated)
URL
https://arxiv.org/abs/2610.34791
PDF
-
Exploring perceptual straightness in learned visual representations
2026-10-26 01:16:37Anne Harrington, Vasha DuTell, Ayush Tewari, Mark Hamilton, Simon Stent, Ruth Rosenholtz, William T. FreemanAbstract
Humans have been shown to use a "straightened" encoding to represent the natural visual world as it evolves in time (Hénaff et al. 2019). In the context of discrete video sequences, "straightened" means that changes between frames follow a more linear path in representation space at progressively deeper levels of processing. While deep convolutional networks are often proposed as models of human visual processing, many do not straighten natural videos. In this paper, we explore the relationship between network architecture, differing types of robustness, biologically-inspired filtering mechanisms, and representational straightness in response to time-varying input; we identify strengths and limitations of straightness as a useful way of evaluating neural network representations. We find that (1) adversarial training leads to straighter representations in both CNN and transformer-based architectures but (2) this effect is task-dependent, not generalizing to tasks such as segmentation and frame-prediction, where straight representations are not favorable for predictions; and nor to other types of robustness. In addition, (3) straighter representations impart temporal stability to class predictions, even for out-of-distribution data. Finally, (4) biologically-inspired elements increase straightness in the early stages of a network, but do not guarantee increased straightness in downstream layers of CNNs. We show that straightness is an easily computed measure of representational robustness and stability, as well as a hallmark of human representations with benefits for computer vision models.
Abstract (translated)
URL
https://arxiv.org/abs/2610.34678
PDF
-
Acute Stroke Classification Using Asymmetric Data Standardization and Orthogonal-Focal Loss Optimized CNN-ViT Cross-Attention Fusion: A Multicenter External Validation Study
2026-10-25 19:43:28Tansel UyarAbstract
Background/Objectives: Rapid differentiation of ischemic and hemorrhagic stroke subtypes is vital for acute management. Although current deep learning models achieve high single-dataset accuracy, they suffer from "shortcut learning" and domain shift in external validation. This study proposes a hierarchical computer-aided diagnostic (CAD) system mimicking emergency triage. Methods: We introduce a 3-channel Radiology-Focused Preprocessing pipeline that feeds radiological Hounsfield Unit (HU) windows into Convolutional Neural Network (CNN) and Vision Transformer (ViT) backbones via asymmetric formats (.mat and .png). The architecture utilizes a novel joint cross-attention fusion network optimized by an Integrated Orthogonal-Focal Loss. Results: Our system achieved a 95.48% F1-score on the internal stroke dataset. However, multi-center external validation (AISD, BHSD, PhysioNet) using a Mask Anchor filter revealed a drop to the 58-62% range, exposing the "internal validation illusion" caused by hardware noise. Critically, models exhibited high precision (77%) but low sensitivity (57%) for ischemic stroke, proving prone to hemorrhage overdiagnosis. Multi-seed variance analysis demonstrated that the DenseNet201+ViT backbone yielded the lowest deviation (0.59) and highest stability, making it the most reliable architecture for real-world clinical integration. Conclusions: To overcome diagnostic challenges, future research must focus on multimodal architectures that combine 3D volumetric extraction with clinical data.
Abstract (translated)
URL
https://arxiv.org/abs/2610.34529
PDF
-
Spatially-Aware Self-Organizing Graph Autoencoders via Localized Hebbian Learning
2026-10-25 14:57:51Robin Ko\c{c}, Hazal Mo\u{g}ultay \"Ozcan, Fato\c{s} T. Yarman VuralAbstract
Traditional autoencoders rely on static network architectures to learn latent representations. Recently we suggested a dynamic architecture inspired by Hebbian plasticity, enabling topological self-organization among convolutional feature maps (R. Koç et al., Proceedings of the SIU, 2026). Early implementations of this paradigm infer relationships among feature maps using global average pooling and model their interactions through scalar-valued connections. This approach falls short to fully exploit the underlying spatial information, embedded in input images. Furthermore, abrupt transitions between different loss functions and training dynamics can introduce representation shocks, leading to unstable feature learning. In this paper, we introduce a Spatially-Aware Self-Organizing Graph Autoencoder (S-LooM) to address these structural bottlenecks. By using spatial cross-correlation, and spatial kernels, S-LooM establishes dynamic connections among feature maps. We replace static scalar message passing of autoencoders with learnable spatial kernels and eliminate high-frequency deconvolutional artifacts observed in decoders using nearest-neighbor upsampling. Via a soft-blending training curriculum, the latent topology aligns smoothly during training. Our experiments show that S-LooM yields a more stable topology, compared to the state of the art dynamic architectures. Meaning, the graph structure that emerge has more resistance to feature entanglement and noise. It forms functional communities responsible for visual attributes, such as illumination, shape and texture even under high connection densities.
Abstract (translated)
URL
https://arxiv.org/abs/2610.34346
PDF
-
Hybrid Mamba-Transformer Network for Single-Shot 3D Reconstruction from Fringe Patterns
2026-10-25 01:58:48Xinjie Zhou, XiaoLei LiAbstract
Deep learning facilitates rapid single shot three dimensional (3D) reconstruction using fringe projection profilometry (FPP), but recovering accurate surface height from a single high frequency fringe image remains challenging because both long-range spatial consistency and fine geometric details must be preserved. Convolutional networks are limited in modeling long range dependencies, whereas window-based Transformers establish global interactions only progressively with increasing depth. To address these limitations, a hybrid Mamba Transformer network is proposed for fringe to height regression. The network adopts a Swin based U shaped architecture and introduces visual state space modeling at the intermediate resolution encoder stage. An axial and dilated vision state space (ADVSS) block is further developed to enhance prescan feature encoding through local, dilated, and axial depthwise convolutions while retaining four directional selective scanning. This design combines linear complexity long range modeling with direction aware preservation of local fringe structures. Experiments on a publicly available FPP dataset show that the proposed method outperforms hNet, SwinConvUNet, UHRNet, and HiDNet in mean absolute error(MAE), root mean square error (RMSE), absolute relative error, and structural similarity index measure (SSIM). Using only one deformed fringe image, the proposed method achieves an RMSE of 0.548 mm and an SSIM of 0.9985, reducing RMSE by 65.2% and 59.6% relative to UHRNet and HiDNet, respectively. These results demonstrate the effectiveness of combining selective state space modeling with hierarchical window based attention for accurate single-shot FPP reconstruction.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33988
PDF
-
A Computer Vision Approach to Visual Fraud Detection in Phishing Websites Using YOLOv8
2026-10-24 20:41:40Basil Sajid ShaikhAbstract
Phishing remains one of the most common vectors for financial and identity fraud, and most detection systems still rely on inspecting a page's URL, HTML markup, or domain registration history. These signals are easy for an attacker to rotate or obfuscate, and they say very little about what actually convinces a victim to hand over a password or a card number: the way the page looks. This paper describes a visual, image-based approach to phishing detection that treats a rendered webpage the same way a human eye would, as a picture that either matches a trusted brand or doesn't. A YOLOv8 convolutional neural network was trained to classify full-page website screenshots as phishing or legitimate based on layout, logo placement, color scheme, and login-form structure, rather than on text extracted from the page. The system reached 92% classification accuracy on a held-out test set, processed a single screenshot in roughly 100 milliseconds, and, after a round of data augmentation aimed specifically at lighting, compression, and scaling variation, cut the false-positive rate by 11% relative to the pre-augmentation baseline. The paper walks through the dataset construction, the augmentation strategy, the model architecture and training setup, and the resulting performance, and closes with a discussion of where this kind of visual detector fits alongside, rather than instead of, existing URL- and content-based defenses.
Abstract (translated)
URL
https://arxiv.org/abs/2609.34015
PDF
-
Energy-Based Fault Detection and Isolation Framework for Flat Port-Hamiltonian Mechanical Systems
2026-10-24 13:50:17Johnny Garcia, Nicolas Salguero, Naveed Iqbal, Brahim Brahmi, Ramy RashadAbstract
Fault diagnosis during regulated motion requires informative signals even when feedback attenuates tracking deviations. This paper develops an energy-based diagnostic framework that constructs mechanical port-power residuals without a dedicated dynamic observer. Spectral Hamiltonian Algebraic Power Evaluation (SHAPE) combines port-Hamiltonian variables and differential flatness to generate nominal power references from planned motion for fully actuated mechanical systems with collocated actuation. Subtracting these references from commanded effort multiplied by measured flow yields residuals whose final evaluation requires neither recursive observer updates nor measured-state dynamics calculations. Continuous wavelet transform (CWT) scalograms and a shared-encoder convolutional neural network are used to distinguish nominal operation, actuator loss of effectiveness, anomalous friction, and vibration from complete trajectories. Evaluation uses a simulated six degree of freedom Kinova manipulator under model predictive control and fixed plant-model mismatch, with single faults at a specified joint. Across five training seeds and 3000 held-out test runs, SHAPE-CWT achieves a mean accuracy of 84.69 percent, versus 81.67 percent for torque residuals and 97.17 percent for the generalized momentum observer under common CWT processing. The respective sample standard deviations are 0.70, 0.70, and 0.37 percentage points. These results demonstrate useful fault-type discrimination from algebraic power residuals, while severity-excitation profiles and offline velocity perturbations reveal limits to their diagnostic capability.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33679
PDF
-
Promise and Limits of Cross-Architecture Knowledge Distillation for Lightweight Medical Vision Transformers
2026-10-24 07:58:46Shuaibu Shehu (SR University), Elijah M. Flomo (SR University), Mohammad Safiya (GITAM University), Anurodh Kumar (SR University), Subodh Kumar (Dr. KNS Memorial Institute of Medical Sciences)Abstract
Running deep models for medical image analysis at the point of care is challenging with standard architectures: convolutional neural networks (CNNs) are often too heavy for edge devices, while Vision Transformers (ViTs) require massive training datasets to compensate for missing inductive biases. This study investigates how far the dual-token distillation used to train data-efficient ViTs can be pushed when applied across architectures, from a CNN-based teacher into a lightweight ViT student. LiteMed-ViT is introduced as a dual-token ViT featuring a convolutional stem and a class-balanced distillation objective; at 0.234M parameters, LiteMed-ViT carries 47.8x fewer parameters than its ResNet18 teacher at a memory footprint of just 0.89 MB. Evaluated against three compact CNN baselines on three MedMNIST subsets of varying modality and class balance, LiteMed-ViT attains higher accuracy than all three baselines on BloodMNIST (95.05%) and two on PathMNIST (89.15%). Under MedMNIST-C corruptions, it is at least as robust as every compact CNN across all subsets, outperforming them on BloodMNIST and PathMNIST without declining in relative standing as severity increases. Particular attention is devoted to identifying the exact conditions where performance plateaus. On DermaMNIST, LiteMed-ViT's balanced accuracy remains up to 1.9 points below the strongest compact CNNs and does not benefit from higher input resolutions up to 224 pixels, where ResNet18 gains 12.6 points. Stronger teachers do not yield a more accurate student, and overconfident ones lower its DermaMNIST balanced accuracy unless calibrated.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33520
PDF
-
Energy Efficient Lung Tumor Segmentation with a modified CBAM ENet Skip Model
2026-10-24 06:06:40Sharan Thummagunti, Aayushi Padia, Abhiram Koppuravuri, Prabhu Prasad B M, G N GirishAbstract
Lung tumor segmentation plays a vital role in early detection and treatment planning of lung cancer. Although state-of-the-art deep learning models achieve high dice score coefficients (DSC), each forward pass requires computing large amounts of floating point operations, making them computationally expensive, requiring GPU acceleration, and having slow inference speed, limiting real-world clinical deployment. We propose a lightweight, energy-efficient model that leverages the ENet architecture for its real-time inference capability and low computational cost, enhanced with UNet-style skip connections between encoder and decoder stages for feature reuse and the lightweight Convolutional Block Attention Module (CBAM) for improved feature representation. The model is trained on publicly available data from The Cancer Imaging Archive (TCIA) via the Medical Segmentation Decathlon Challenge (MSD) and evaluated on the Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) dataset. Our model achieves a DSC of 0.90812 (threshold of 0.5) with its compact architecture of 430,052 parameters and 0.549 Giga Multiply-Accumulate operations (GMAC), making it up to 10 times faster, requires 79 times less GMAC than UNet, and has 22 times fewer parameters than SegNet. These characteristics make it well-suited for deployment in clinical settings where computational resources are limited and decrease the cost of utilizing such a system. Additionally, the explainable AI technique of Grad-CAM is used to provide visual interpretability of the model's predictions and to identify regions where segmentation performance requires improvement.
Abstract (translated)
URL
https://arxiv.org/abs/2610.33479
PDF
-
EigenGradCAM with AugSmooth: Enhancing Explainability and Precision in Multi-Stage Alzheimer's Disease Detection
2026-10-23 09:01:17Arsham Azam, Sagar Ashraf, Tayyaba Farhat, Rasikh Ali, Sheeraz AkramAbstract
Alzheimer's disease (AD) is a progressive neurological disorder associated with memory loss, cognitive decline, and behavioral disturbances. Early and accurate diagnosis is essential, yet MRI-based deep learning models often lack interpretability, limiting their clinical use. This study presents an explainable deep learning approach for four-class AD staging using 2D axial MRI images. The method combines eigenvector-based Grad-CAM with gradient smoothing to improve saliency localization and heatmap stability. Principal component analysis is applied to gradient-weighted convolutional layers, while Gaussian noise is added to saliency weights before decomposition. To address class imbalance in the Moderate Dementia category, Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP) generates synthetic samples to balance the four-stage training distribution. Custom convolutional neural networks are trained on the Best Alzheimer MRI Dataset, achieving 97.2% test accuracy, 97.0% balanced accuracy, and a Matthews correlation coefficient of 0.944. The area under the ROC curve ranges from 0.96 to 0.99 across classes. Generated heatmaps highlight the hippocampus and entorhinal cortex, regions associated with Alzheimer's disease biomarkers. These findings suggest that the proposed approach combines strong classification performance with improved model interpretability, although further clinical validation is needed.
Abstract (translated)
URL
https://arxiv.org/abs/2610.32374
PDF
-
Representation Learning via Composite Subspace Flow Matching
2026-10-23 07:11:07Jos\'e Afonso, M\'ario FigueiredoAbstract
Distilling semantic meaning from raw image data remains a challenge in machine learning. Current self-supervised paradigms face a trade-off: joint-embedding architectures produce relevant features by aggressively discarding intra-class variance, irreversibly spatial and reconstruction. Conversely, generative models preserve spatial details but struggle to isolate semantics, as their optimization is dominated by pixel variations. To bridge this divide, we propose composite subspace flow matching (CSFM). Rather than corrupting data with unstructured isotropic noise, CSFM formulates representation learning as the variance-minimizing inversion of a deterministic degradation curriculum across spectral, color, and illumination subspaces. By bounding trajectory variance with hard temporal style truncation, a capacity-constrained encoder is driven to ignore transient style artifacts and encode persistent content. Empirical evaluations across CIFAR-10, CIFAR-100, and STL-10 show that CSFM yields competitive discriminative transferability while preserving generative synthesis across both convolutional and vision transformer architectures. By avoiding the collapse pathologies of non-generative methods, CSFM forms a smooth latent space that outperforms standard optimal transport flows on linear probing and few-shot classification, while enabling coherent synthesis and trajectory interpolation. These results confirm that steering the physical dynamics of generative flows offers a scalable paradigm for learning representations that are simultaneously linearly separable and generatively invertible.
Abstract (translated)
URL
https://arxiv.org/abs/2610.32256
PDF
-
Patronizing and Condescending Language Detection in English and Mandarin
2026-10-22 18:44:00Xinyi Vicky Xiang, Catherine Qingyun Wang, Paula Cort\'es LemosAbstract
Patronizing and condescending language (PCL) is a form of harmful language that belittles and assumes pity for vulnerable groups, reinforcing negative societal stereotypes. However, unlike overt hate speech, it is often difficult to detect, even for human judges. This paper proposes a system for the automated detection of PCL. Our first approach uses static word embeddings and a convolutional neural network for classification, while our second approach uses pre-trained BERT embeddings fine-tuned for the PCL task. Our second approach was considerably more successful, and achieved an F1 score of 0.528 over the development set.
Abstract (translated)
URL
https://arxiv.org/abs/2610.31808
PDF
