CNN
-
'What's That Sound?': A Versatile, Robust, and Lightweight Convolutional Transformer for Environment Sound Recognition
Abstract
The conventional hearing aid is both costly and lim- ited in usage, as it is not intended to detect non-speech audio. Our objective is to develop a machine learning solution to provide a more accurate and affordable mechanism to identify surrounding sounds to improve the safety of the hearing impaired, i.e., if a car is honking behind pedestrians, or a gunshot is fired, and they need to move away from the source. By adding randomized augmentations to audio, concatenating a Mel-Frequency Cepstral Coefficients (MFCCs) diagram and a log-mel Spectrogram, and including Convolutional Neural Networks (CNNs) in a Trans- former architecture, the Randomized Audiomentational Layered Convolutional Transformers (RALCT) model efficiently extracts features from diversified audio representations. In addition, RALCT is small enough, with only approximately 310,000 parameters, to be deployed into mobile devices. Experimental results on the UrbanSound8K dataset resulted in an accuracy consistently over 93% for all variations of RALCT with the highest at 94.56%, reaching state-of-the-art levels. To leverage the capabilities of this technology, a mobile app is developed to be integrated with the model to provide real-time safety control. RALCT thus represents a robust, lightweight, affordable, and versatile deep learning tool to aid the navigation and safety of the hearing impaired.
Abstract (translated)
URL
https://arxiv.org/abs/2609.27762
PDF
-
EA-LiteUNet: An Edge-Adaptive and Resource-Efficient U-Net for Boundary-Sensitive Dermoscopic Image Segmentation
2026-08-16 05:20:39Wang Jiangtao, Nur Intan Raihana Ruhaiyem, Fu Panpan, Yang Yu, Huang YanAbstract
Accurate boundary delineation remains a persistent challenge in dermoscopic image segmentation because of blurred lesion margins, heterogeneous textures, and complex background artifacts. From a signal-processing perspective, lesion boundaries represent high-frequency components that are highly susceptible to aliasing, noise amplification, and information loss. Consequently, repeated downsampling and feature transformations in conventional convolutional architectures often lead to severely degraded boundary representations. To address these limitations, we propose EA-LiteUNet, an edge-adaptive and computationally efficient U-Net variant specifically designed for boundary-sensitive medical image segmentation. The architecture integrates three core mechanisms: (1) boundary-aware representation learning to suppress aliasing and preserve high-frequency structural details; (2) attention-guided feature modulation to selectively enhance boundary-relevant responses across multi-scale features; and (3) a resource-adaptive inference strategy to dynamically balance segmentation accuracy and computational efficiency. Extensive evaluations across three public dermoscopic datasets demonstrate that EA-LiteUNet consistently achieves superior boundary precision. Specifically, on the ISIC 2018 dataset, the method significantly reduces the 95% Hausdorff Distance (HD95) to 12.89 pixels while maintaining a robust Dice score of 92.08%. Notably, this strong performance is achieved with an ultralightweight configuration of merely 0.29M parameters and 1.17 GFLOPs. Ablation studies further validate the complementary effects of these components, confirming their contribution to enhanced boundary fidelity and stable optimization.
Abstract (translated)
URL
https://arxiv.org/abs/2608.15537
PDF
-
CG-GLORE: A Conjugate Gradient-Based Global-Local Regularization Network for Sparse-View CT Reconstruction
2026-08-15 14:08:44Tran Xuan Hieu Le, Doanh C. Bui, Vu Trung Duong Le, Hoai Luan Pham, Khang Nguyen, Mai K. Nguyen, Tu Bao Ho, Yasuhiko NakashimaAbstract
Sparse-view computed tomography (CT) reduces radiation dose by acquiring fewer projection views, but the resulting inverse problem is highly ill-posed and often produces severe streak artifacts. Existing deep reconstruction methods have achieved promising performance, yet many rely on first-order updates or large regularization networks, which can be less effective in ill-conditioned settings. We propose \textbf{CG-GLORE}, a compact deep unrolling framework inspired by second-order optimization for sparse-view CT reconstruction. Each unrolled stage uses a CG-solved linear system based on a structured Hessian surrogate: it retains the physics-induced curvature of the data-fidelity term while using an identity approximation for the learned regularization term. Thus, the method is second-order-inspired rather than an exact Newton method for the full learned objective. To model image priors, we design a Global-Local Regularization Network (GLORE), which combines convolutional local feature extraction with a Long-Range Dependency Representation module based on sparse patchification and Nyström attention. This design captures anatomical details and non-local dependencies while maintaining practical complexity. Experiments on AAPM and DeepLesion under multiple sparse-view and noise settings show that CG-GLORE achieves strong quantitative performance, stable convergence, lower noise power, and improved visual fidelity compared with representative reconstruction methods.
Abstract (translated)
URL
https://arxiv.org/abs/2608.15246
PDF
-
TERRA: A Hierarchical Parallel Training and Memory Orchestration Framework for High-Resolution AI-based Earth Modeling
2026-08-15 12:52:48Ruohan Wu, Ziqi Zhu, Yang Zhao, Jiarui Tang, Yingzhe Cui, Junshi Chen, Zhao Jing, Jun Shi, Hong AnAbstract
Training high-resolution AI-based Earth forecasting models is memory-intensive. Window-based Swin Transformers reduce the quadratic cost of global attention, but existing distributed systems such as AERIS primarily target pixel-level models and do not jointly support convolutional sampling modules and shifted-window execution. Long-lead rollout finetuning further increases activation memory. To address these challenges, we present TERRA, a hierarchical parallel training framework for high-resolution Earth forecasting. TERRA introduces Sampling-Aware Window, Sequence, and Tensor Parallelism (SAWSTP), which preserves spatially contiguous layouts for sampling modules and routes tokens into topology-aware ragged window layouts for Transformer execution. For long-lead finetuning, Memory Orchestration (MO) provides rollout-aware checkpoint planning and combines input buffering with budget-constrained activation offloading. Experiments on the $1/12^\circ$ GLORYS-based Wenhai workload show that TERRA supports models with up to 11.4B parameters on 96 H200 GPUs and sustains up to $39.76$ PFLOPS, achieving $65.0\%$ strong-scaling and $94.1\%$ weak-scaling efficiency. Compared with checkpoint-only policies, MO further reduces peak allocated GPU memory by $32.2\%$--$51.8\%$ with at most $20.0\%$ step-time overhead, which makes finetuning with smaller patch sizes and longer rollouts feasible for improved forecasting accuracy.
Abstract (translated)
URL
https://arxiv.org/abs/2608.15211
PDF
-
A Unified Backbone--Expert Framework with Relation-Token and Residual--Classifier Interfaces for Automatic Modulation Recognition
2026-08-15 10:26:42Zhixiang Deng, Houbiao Li, Zongyong CuiAbstract
Automatic modulation recognition (AMR) faces distinct representation bottlenecks under varying observation lengths, where a single model architecture often fails to excel. To address this, we propose a unified backbone-expert framework with a common convolutional state-space backbone and two specialized interfaces. For short sequences, we inject explicit lag-aware complex-plane descriptors as relation tokens before encoding to compensate for information loss. For long sequences, we design a gated multi-scale residual refinement module to correct the feature map, combined with a fixed-averaging classifier collaboration to harness complementary evidence. Our framework achieves overall average accuracies of 67.28 \pm 0.14% on RML2016.10b and 87.19 \pm 0.77% on HisarMod2019 (mean \pm sample standard deviation over three runs), respectively. The framework's efficacy is further validated through three-seed ablations, native-length cross-configuration tests, and controlled window studies, confirming the benefit of expert-interface decoupling over one-size-fits-all architectures.
Abstract (translated)
URL
https://arxiv.org/abs/2608.15160
PDF
-
DualMiT-Net: Local-Global Transformer-Convolutional Fusion for Breast Mass Segmentation in Mammographic Regions of Interest
2026-08-15 04:08:26Alibek Kamiluly, Milana Muratova, Yash Patel, Fan LiAbstract
Breast mass segmentation is an important step in computer-aided mammography, but it remains difficult because masses can have low contrast, irregular shapes, and boundaries that blend with surrounding breast tissue. To address this problem, we present DualMiT-Net, a dual-branch network that uses both a focused view of the mass and a wider view of the surrounding tissue. The local branch uses a Mix Transformer (MiT-B5) encoder to learn mass shape, texture, and boundary information, while the global branch uses an EfficientNet-B5 encoder to learn surrounding breast context. Features from the two branches are shared at the deeper encoder levels and are then progressively fused in a single decoder. A spatial gate controls how much global information is added during decoding. We also evaluated four input representations and selected a percentile-windowed mammogram combined with a Gabor texture response. The model was trained and evaluated on the mass subset of the Curated Breast Imaging Subset of the Digital Database for Screening Mammography (CBIS-DDSM) using a patient-level split. Across three training runs, DualMiT-Net with exponential moving average weights achieved a mean Dice coefficient of 0.9375 and a mean Intersection over Union of 0.8834. It also achieved better Dice and IoU scores than six standard encoder-decoder baselines trained using the same data and training settings. These results show that combining local mass information with wider breast context can provide accurate and consistent breast mass segmentation.
Abstract (translated)
URL
https://arxiv.org/abs/2608.15019
PDF
-
MagnifiQ: Patch-aware Text Guided Progressive Upscaling for High-Resolution Image Restoration
2026-08-14 17:56:04Mahesh Reddy, Yashesh Savani, Antoine Mercier, Hong Cai, Fatih Porikli, Guillaume BergerAbstract
High-resolution image restoration from degraded inputs is challenging because it must preserve global structural consistency while recovering fine-grained local details, especially at 4K resolution where direct diffusion-based restoration is computationally expensive and prone to repeated or inconsistent textures. In this work, we introduce MagnifiQ, an image restoration framework that progressively upscales and restores images across resolutions, e.g., from 1024x1024 to 4096x4096. Our approach leverages a pre-trained text-to-image diffusion model such as SDXL and adapts it for more scalable high-resolution inference by replacing its original self-attention layers with convolutional operations whose computational cost grows linearly with image resolution. We further propose a progressive upscaling strategy that iteratively restores images over multiple resolution stages, refining each intermediate output rather than directly hallucinating the final 4K image, thereby improving global coherence and reducing high-resolution artifacts. To enhance local details while controlling content drift, MagnifiQ uses patch-specific text prompts that provide spatially localized semantic guidance during restoration. Extensive experiments on synthetic and real-world degraded images show that MagnifiQ outperforms prior diffusion-based restoration methods in perceptual quality and human preference, producing sharper textures and more coherent 4K results while offering practical speed--quality trade-offs through its scalable backbone and progressive design.
Abstract (translated)
URL
https://arxiv.org/abs/2608.14543
PDF
-
LightTeaNet: A Weakly Supervised Lightweight CNN for Multi-Label Tea Leaf Disease Detection and Localization
2026-08-14 10:48:58Naif Haider Chowdhury, Md Rahim, Syed Farhan Hasan, Murad Hasan, Prithwiraj BhattacharjeeAbstract
Tea is known as an important crop in many parts of South and Southeast Asia, yet the production of tea is still hampered by the multiple diseases that decrease the quantity and quality. Traditional methods of inspection, which are manual, are not consistent, labor-intensive, and depend on extensive monitoring. This paper introduces a lightweight convolutional neural network (CNN) designed for weakly supervised multi-label classification and disease localization in tea leaves called LightTeaNet. LightTeaNet learns directly from image-level labels and employs Class Activation Mapping (CAM) to localize disease-affected regions automatically, unlike conventional object detection models such as YOLO, which require extensive bounding box annotations. For Parameter efficiency, the network integrates Depthwise Separable Convolutions, and for enhanced feature discrimination, it integrates Channel Attention. LightTeaNet has achieved a Precision of 0.9615, a Recall of 0.8772, and an F1-score of 0.9179, while it shows mAP@0.50=0.1810 without any manual annotations, which delivers a competitive localization performance in the experimental results. These results validate the model as an interpretable as well as a resource-efficient framework for intelligent disease monitoring in agriculture.
Abstract (translated)
URL
https://arxiv.org/abs/2608.14178
PDF
-
CSG-Mamba: A Convolutional Scoring Gating Vision State Space Network for Endoscopic Polyp Segmentation
2026-08-14 09:54:52Yuliang Wang, Jiaqi Wu, Jiaye Song, Shuxia RenAbstract
Accurate polyp segmentation is critical for computer-aided colonoscopy, yet endoscopic images often contain low-contrast boundaries, mucosal texture interference, specular highlights, and device-dependent appearance shifts. Vision State Space Models (SSMs) provide efficient long-range modeling with linear complexity, but existing Vision Mamba segmentation models typically convert 2D features into 1D scanning sequences, which may weaken local geometric continuity and over-smooth irregular contours. We propose CSG-Mamba, a convolutional scoring gating Vision State Space network for endoscopic polyp segmentation. Built on a VM-UNet-style asymmetric U-shaped encoder-decoder, CSG-Mamba inserts a Convolutional Scoring Gating (CSG) module at the semantically rich bottleneck. CSG generates a local spatial score map through pointwise and large-kernel depthwise convolutions and recalibrates state-space features by multiplicative gating. Experiments with three random seeds show that CSG-Mamba achieves 0.9220 Dice and 15.87 HD95 on Kvasir-SEG, and 0.7418 Dice and 0.6570 mIoU on CVC-ColonDB, outperforming the baselines on most overlap and recall metrics while maintaining competitive boundary accuracy.
Abstract (translated)
URL
https://arxiv.org/abs/2608.14146
PDF
-
RDSE: Real-Time Directional Speech Enhancement Framework for Dual-Mic Commodity Smartphones
2026-08-14 09:03:34Chinmay Deo, Danish Mahajan, Soudeep Ghoshal, Himanshu BuckchashAbstract
Audio-visual zooming on mobile devices is fundamentally constrained by limited microphone count, compute resource, unknown array geometry, and weak assumptions on real-world acoustic conditions. We present RDSE: Real-Time Directional Speech Enhancement Framework, a hybrid pipeline that combines traditional signal processing and modern machine learning methods for dual-microphone low-end smartphones. Unlike tightly coupled AV systems that continuously use visual feeds or embeddings, RDSE decouples visual interaction from feature inference, using camera input solely to parameterize the steering vector for spatial filtering. The proposed system uses four modules: dereverberation network, a beamformer with a temporal convolutional network, and a MetricGAN based denoiser. Extensive evaluation on benchmark data and real-world recordings demonstrates effective zooming without precise geometry calibration. Comparative experiments show competitive performance to existing methods. Proposed system is rigorously tested for statistical validity, ablation study, latency profiling, and practicality through real-time live-streaming.
Abstract (translated)
URL
https://arxiv.org/abs/2610.12476
PDF
-
PILOT: Privileged Imitation Learning for End-to-End Motion Planning of Autonomous UAVs under Partial Observability
2026-08-14 08:43:59Qingrui Zhang, Feng Xue, Xiang Zhou, Chenghao YuAbstract
Autonomous navigation in cluttered environments is hampered by partial observability and dynamic constraints. This paper presents PILOT, a constraint-aware privileged imitation learning framework for vision-based end-to-end UAV motion planning under partial observability. The framework distills planning strategies from a computationally intensive optimal control expert into a student policy regularized toward safety and dynamic requirements via a dual-objective loss function. To mitigate partial observability, a spatiotemporal perception fusion module using a Temporal Convolutional Network (TCN) is developed to integrate historical depth images and odometry. This module infers task-relevant latent context from historical observations, enhancing spatial awareness beyond the instantaneous FOV without maintaining persistent map memory. A trajectory parameterization layer mapping network outputs to a structured trajectory, while enabling explicit continuity, dynamic-consistency, and obstacle soft penalties during training, encouraging constraint satisfaction for unseen observations without formal guarantees. Simulations on quadrotor and fixed-wing aircraft demonstrate that PILOT achieves performance comparable to the privileged expert while reducing computational overhead by over 80\%. Successful indoor and outdoor zero-shot deployment confirms the practical feasibility and cross-domain generalization of the planner.
Abstract (translated)
URL
https://arxiv.org/abs/2608.14082
PDF
-
Incision trajectory tracing for electrosurgical navigation by CNN-based knife contacting frames extraction method
2026-08-14 02:05:05Yu Chun Wang, Kaixu Chen, Naoto Ienaga, Yoshihiro KurodaAbstract
Background and Objective: Image-guided surgical navigation has been actively studied because of its advantage of identifying subsurface targets and critical structures, whereas it requires incision trajectories to update the preoperative three-dimensional model dynamically during the surgery. The novelty of this study is the thermal feature distinguishment of whether the electric tools contacting the tissue by Convolutional Neural Network (CNN), and the extraction of the knife contacting frames, to form incision trajectories which can meet with the requirement during the surgery. Methods: This study firstly verified that CNN can classify the thermal images of electric knife and ultrasonic cutter operations separately, and can raise the accuracy of the incision trajectories derived from the connection of the thermal intensity centroid of the frames predicted by CNN as contacting. Results: Our results obtained by employing the electric knife not only reveal a remarkably high accuracy 97.2 % in CNNs identification, but also can achieve an error reduction as high as more than 2.5 times of the incision trajectory prediction as compared to those proceeded in the conventional method. Besides electric knife, the results obtained by employing another electric tool, ultrasonic cutter, reveal a high accuracy up to 93.7 %. Conclusion: In this study, we ensured the possibility of CNN in distinguishing electric tools contacting with the tissue, and confirmed that the proposed method has not only overcome the problem of missing trajectories which usually occurs in the convolutional long-short term memory method but also achieved a remarkable improvement of the accuracy with less limitation.
Abstract (translated)
URL
https://arxiv.org/abs/2608.14749
PDF
-
TRUE-Colon: Exposing a Consistent Transfer Asymmetry in Real-Time Polyp Detection
2026-08-13 19:13:54Sebastian Doerrich, Andreas Franz Schwab, Francesco Di Salvo, Shyam Nandan Rai, Hanh Huyen My Nguyen, Christian LedigAbstract
Computer-aided detection (CADe) systems for colonoscopy promise to reduce clinical miss rates, yet reliable real-world deployment remains elusive. This translational gap stems in part from a structural flaw in model development: the reliance on curated datasets that under-represent the long negative stretches and procedure-related artifacts characteristic of routine examinations. Training and evaluating architectures strictly on these lesion-centric benchmarks creates an illusion of success, since such benchmarks cannot capture clinically crucial metrics. To expose this gap, we establish TRUE-Colon, a standardized benchmarking protocol that measures key deployment characteristics alongside localization accuracy, and evaluate four real-time architectures (Faster R-CNN, YOLOv8, YOLOv11, RT-DETR) across curated benchmarks (SUN, PICCOLO) and 60 unedited, full-length procedures (REAL-Colon). We observe a consistent transfer asymmetry: models trained strictly on curated clips suffer a severe performance collapse when evaluated on full procedures, whereas procedure-trained models substantially improve rejection of non-polyp content on REAL-Colon, and largely retain their accuracy on curated benchmarks. Beyond transferability, we find that the Transformer detector attains the strongest sensitivity and the earliest, most persistent detections, while the convolutional detectors stay competitive at a higher throughput. Together, these results indicate that both training and benchmarking for deployable CADe should shift from curated, lesion-centric clips toward full-procedure data and deployment-relevant operating points. Source code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2608.13711
PDF
-
TabSOM: A tabular-to-image encoding method based on self-organizing maps
2026-08-13 17:35:37David Chushig-Muzo, Mar\'ia \'Angeles Rodr\'iguez de Cara, Eva Milara, Francisco J. Lara-Abelenda, Luis Zhinin-Vera, Diego H. Peluffo-Ord\'o\~nezAbstract
Tabular-to-image methods have emerged as novel approaches to leverage the high predictive performance of convolutional neural networks and vision transformers. They convert tabular data into image representations, mapping each feature at a fixed pixel location derived from a dimensionality-reduction method (e.g., t-SNE, UMAP, PCA). However, they encode only the marginal value of each feature and discard information about feature relationships. We propose TabSOM, a tabular-to-image encoding built on the Self-Organizing Map (SOM), which provides: (i) a spatial layout in which every input feature occupies a fixed canvas position derived from its component plane via collision-free Hungarian assignment; and (ii) a graph that captures pairwise feature relationships derived from the SOM component planes. The resulting image stacks two multi-scale node channels: one encodes feature values at fixed scales, while the other encodes pairwise feature interactions as spatial connections between related features. Two SOM-derived interpretability approaches are introduced: a prototype-inspired partial dependence plot and a class--separation importance score. Benchmarked against twelve existing tabular-to-image methods across public binary-classification datasets, TabSOM ranks first or second on every dataset and achieves the lowest variance of any method evaluated. Interpretability obtained with TabSOM was validated against Random Forest, XGBoost, and SHAP, the class-separation score shows reasonable agreement with established baselines on the top-ranked features while capturing complementary structural information from input data. These results demonstrate that TabSOM provides an effective and interpretable approach for applying deep learning architectures to tabular data, bridging the performance--interpretability gap in this domain.
Abstract (translated)
URL
https://arxiv.org/abs/2608.13513
PDF
-
MLLM-Routed Heterogeneous Ensembles for Robust Cross-Dataset Image Classification
2026-08-13 16:45:24Daniel Perkins, John Squires, Janou Milligan, Chandra Raskoti, Linda UngerboeckAbstract
Modern image classification models excel when trained on single task-specific datasets but often struggle to generalize across domains and difficulty levels. We propose ARMDIL, an Adaptive Router for Multi-Domain Image classification with LLMs. ARMDIL is an ensemble that uses a multimodal large language model (MLLM) agent to dynamically route each image to the most suitable vision backbone. Our diverse ensemble employs convolutional neural networks (ResNets), self-supervised representation learners (SSL), and vision-language models (VLMs), each trained on a unified label space constructed from multiple image datasets with differing distributions and characteristics. Empirical evaluations illuminate the distinct capabilities and vulnerabilities of each architecture across disparate visual domains. Crucially, we show that ARMDIL effectively navigates these trade-offs, performing competitively with specialized training-based routers. Furthermore, it drastically improves adaptability by allowing new information to be integrated via simple prompt modifications, while enhancing interpretability through natural language reasoning traces. These advances in cross-dataset image classification pave the way for more reliable general-purpose vision systems such as AI assistants and autonomous robots.
Abstract (translated)
URL
https://arxiv.org/abs/2608.13463
PDF
-
Sign Language Video Synthesis via Loss-Guided Multi-Expert GANs
2026-08-13 15:32:40Dingzhan Nong, Zhihao Ren, Ziqi Li, Tim LoAbstract
This preliminary technical report presents a framework for sign language video synthesis using a loss-guided multi-expert Generative Adversarial Network (GAN) to enhance communication for individuals with hearing impairments. Three specialized discriminators -- global, hand, and head -- each guide a corresponding expert branch in the generator toward a distinct visual region, enabling implicit feature specialization without explicit diversity losses. To stabilize this multi-discriminator system, whose early-phase training otherwise exhibits chaotic dynamics, we introduce a United Loss consensus mechanism that regularizes each discriminator toward the ensemble average at a 10% weight. Each branch further adopts a dual-pathway convolutional-transformer design with learnable AdaptiveFeatureFusion, balancing the stability of convolutions against the detail of windowed self-attention. The generator is trained using an alternating three-mode schedule (discriminator, holistic generation, branch-specialized generation). On a custom 156GB dataset with a filtered test set that removes easy and repetitive samples, our 0.2B-parameter variant achieves 29.8 PSNR and the 1.3B-parameter variant achieves 30.7 PSNR, with inference VRAM footprints of 1.5 GB and 8 GB respectively, enabling deployment on consumer-grade hardware. Full ablation studies remain ongoing due to the 2-3 month training cycle on a single GPU. The system was showcased at the 2025 Hong Kong Frontier Technology Summit.
Abstract (translated)
URL
https://arxiv.org/abs/2608.13368
PDF
-
Physics-informed distribution of relaxation times estimation and latent-space condition monitoring of solid oxide fuel and electrolysis cells from electrochemical impedance spectroscopy
2026-08-13 14:33:33\v{Z}an Gorenc, \v{Z}iga Gradi\v{s}ar, Felix M\"utter, Vanja Suboti\'c, Pavle Bo\v{s}koskiAbstract
Estimating the distribution of relaxation times (DRT) fromelectrochemical impedance spectroscopy (EIS) is an ill-posed inverse problem that is highly sensitive to regularisation choices. We propose a physics-informed convolutional autoencoder that estimates DRT directly from EIS data without spectrum-specific tuning. A discretised relation between impedance and the DRT is embedded in the training process, constraining the network to produce impedance-consistent distributions. The model resolves overlapping relaxation processes in synthetic two-ZARC spectra and accurately reconstructs measurements from three independent solid oxide fuel and electrolysis cell datasets, with range-normalised errors below 1.1%. Decoder-probe analysis shows that the learned latent representation is organised according to relaxation timescale. Distances in this latent space capture operating changes, hydrogen-shortage events, and long-term degradation. The same lightweight architecture is applied across all datasets without modification, providing consistent DRT estimation and an interpretable basis for condition monitoring.
Abstract (translated)
URL
https://arxiv.org/abs/2608.13305
PDF
-
UniCon-Former: Unified Convolution Transformer is All You Need for Hand Gesture Recognition
2026-08-13 13:19:51Mallika Garg, Debashis Ghosh, Pyari Mohan PradhanAbstract
Convolutional Neural Networks (CNNs) capture local features efficiently but struggle with global context due to their limited receptive field. On the other hand, transformers effectively capture global dependencies through self-attention but suffer from high redundancy and computational costs. Thus, to leverage the advantages of both CNNs and transformers, we propose a unified model (UniCon-Former) that aims to provide robust and efficient performance on dynamic hand gesture recognition. The unified approach helps the model to learn both local and global features. At the beginning of each transformer stage, the convolution projections help in decreasing the dimension of the input vectors of the transformer block. This creates a pyramidal structure at each transformer stage. These features enable the UniCon-Former to reduce resource usage than vanilla transformers, making it flexible for learning multi-scale and high-resolution features, which is required in hand gesture recognition. We have performed experiments with NVGesture and Briareo datasets and achieved state-of-the-art results with fewer parameters and MACs.
Abstract (translated)
URL
https://arxiv.org/abs/2608.13217
PDF
-
Dual-Manifold Geometry Guided Representation Learning: Adaptive Coupling between Kernel and Data Spaces
2026-08-13 02:35:08Wencong Zhang, Yue Zhang, Meiyan Huang, Wei Yang, Qianjin FengAbstract
Deep representation learning has primarily focused on how features evolve across network layers, while largely overlooking the structured geometry embedded in network parameters. We introduce a dual-manifold perspective in which each convolutional layer contains two coupled geometric spaces: a Kernel Manifold induced by convolutional filters and a Data Manifold characterized by intermediate feature representations. Because these manifolds share the same channel space, parameter geometry can provide complementary structural information to guide feature evolution. Based on this insight, we propose Kernel-Guided Feature Transform (KGFT), a lightweight module that derives a geometric guidance matrix from the kernel Gram matrix and uses it to transform the covariance structure of feature representations. Unlike conventional attention mechanisms that reweight feature responses, KGFT explicitly reshapes feature relationships by transferring geometric information from the kernel manifold to the data manifold. To accommodate network hierarchy, we further introduce Exploit and Explore modes with a depth-aware scheduling strategy and a learnable guidance strength that adaptively controls the contribution of geometric transformation. This design promotes geometric alignment in shallow layers while encouraging feature diversity in deeper layers, without imposing excessive constraints on representation learning. Theoretical analysis establishes the validity of the proposed transformation and characterizes its effect on feature covariance. Extensive experiments across CNN- and Transformer-based architectures, including ResNet, ViT, and LLaMA-7B, demonstrate consistent improvements on image classification and arithmetic reasoning tasks, validating the generality and effectiveness of kernel-guided dual-manifold representation learning. Code will be publicly available.
Abstract (translated)
URL
https://arxiv.org/abs/2608.12737
PDF
-
Do CNNs Internally Represent Real and Fake Images Differently? A Hidden-Layer Analysis
2026-08-12 22:48:29Moumita Sen Sarma, Pascal Hitzler, Eugene Y. VassermanAbstract
Fake/synthetic images are increasingly prevalent, but it remains unclear whether Convolutional Neural Networks (CNNs) process real and fake images in the same internal manner. This work examines the hypothesis that CNNs represent real and fake images differently, such that fake images induce different hidden-layer activation patterns even when semantic content is preserved. The hypothesis is evaluated in scene recognition settings using trained CNN models. Dense-layer activations are extracted, and neurosymbolic methods assign semantic labels to selected neurons. For each real test image, corresponding fake images are generated with similar semantic content using object-label-guided text-to-image and image-to-image generation based on Stable Diffusion variants. Paired real-fake activation patterns are then compared statistically. Additional experiments with another dataset, CNN architecture, generative model, and JPEG/blur degradation analysis assess robustness. Results suggest that fake images evoke different hidden-neuron activations, and these differences are not explained only by simple image degradation. Overall, the findings indicate that real and fake images differ in CNN hidden-layer activation behavior at least in some settings, which opens the door for follow-up work on making use of this different behavior to improve fake image detection.
Abstract (translated)
URL
https://arxiv.org/abs/2608.14729
PDF
