Convolutional Neural Networks

Also known as CNN

Ask about this topic

Overview

Convolutional neural networks use shared filters to detect local patterns, then combine them across layers to classify, segment, or predict structured data such as images, video, audio, and sensor signals. Common approaches include residual networks and U-Net-style encoder–decoders, alongside depthwise, dilated, deformable, and input-adaptive convolutions; work also explores 1D and 3D convolutions, physics-informed losses, and quantization or pruning for efficient deployment. CNNs are tested on benchmarks ranging from ImageNet and CIFAR to medical scans, remote-sensing imagery, and time-series datasets, with attention to accuracy, speed, memory, calibration, and performance under domain shift. A central tension is that local convolutional structure can be efficient and data-effective, while some tasks benefit from broader context or attention, and strong benchmark results do not always ensure robust or clinically reliable behavior.

Latest papers

CardsList

401 papers39 papers in the last four weeks, up 26% on the four weeks before. 0.2% of all new papers.

Apr 12, 2026

Topology-Aware PAC-Bayesian Generalization Analysis for Graph Neural Networks

Graph neural networks have demonstrated excellent applicability to a wide range of domains, including social networks, biological systems, recommendation systems, and wireless communications. Yet a principled theoretical understanding of their generalization behavior remains limited, particularly for graph classification tasks where complex interactions between model parameters and graph structure play a crucial role. Among existing theoretical tools, PAC-Bayesian norm-based generalization bounds provide a flexible and data-dependent framework; however, current results for GNNs often restrict the exploitation of graph structures. In this work, we propose a topology-aware PAC-Bayesian norm-based generalization framework for graph convolutional networks (GCNs) that extends a previously developed framework to graph-structured models. Our approach reformulates the derivation of generalization bounds as a stochastic optimization problem and introduces sensitivity matrices that measure the response of classification outputs with respect to structured weight perturbations. By imposing different structures on sensitivity matrices from both spatial and spectral perspectives, we derive a family of generalization error bounds with graph structures explicitly embedded. Such bounds could recover existing results as special cases, while yielding bounds that are tighter than state-of-the-art PAC-Bayesian bounds for GNNs. Notably, the proposed framework explicitly integrates graph structural properties into the generalization analysis, enabling a unified inspection of GNN generalization behavior from both spatial aggregation and spectral filtering viewpoints.

Xinping Yi

School of Information Science and Engineering, Southeast University, Nanjing, China

Neural Network GeneralizationPAC-Bayesian Generalization BoundsConvolutional Neural Networks
AskPDF
Apr 11, 2026

Uncertainty Quantification in CNN Through the Bootstrap of Convex Neural Networks

Despite the popularity of Convolutional Neural Networks (CNN), the problem of uncertainty quantification (UQ) of CNN has been largely overlooked. Lack of efficient UQ tools severely limits the application of CNN in certain areas, such as medicine, where prediction uncertainty is critically important. Among the few existing UQ approaches that have been proposed for deep learning, none of them has theoretical consistency that can guarantee the uncertainty quality. To address this issue, we propose a novel bootstrap based framework for the estimation of prediction uncertainty. The inference procedure we use relies on convexified neural networks to establish the theoretical consistency of bootstrap. Our approach has a significantly less computational load than its competitors, as it relies on warm-starts at each bootstrap that avoids refitting the model from scratch. We further explore a novel transfer learning method so our framework can work on arbitrary neural networks. We experimentally demonstrate our approach has a much better performance compared to other baseline CNNs and state-of-the-art methods on various image datasets.

Hongfei Du, Emre Barut, Fang Jin

The George Washington University · Amazon.com, Inc.

Uncertainty QuantificationConvolutional Neural Networks
AskPDF
Apr 11, 2026

Revisiting the Scale Loss Function and Gaussian-Shape Convolution for Infrared Small Target Detection

Infrared small target detection still faces two persistent challenges: training instability from non-monotonic scale loss functions, and inadequate spatial attention due to generic convolution kernels that ignore the physical imaging characteristics of small targets. In this paper, we revisit both aspects. For the loss side, we propose a diff-based scale loss that weights predictions according to the signed area difference between the predicted mask and the ground truth, yielding strictly monotonic gradients and stable convergence. We further analyze a family of four scale loss variants to understand how their geometric properties affect detection behavior. For the spatial side, we introduce Gaussian-shaped convolution with a learnable scale parameter to match the center-concentrated intensity profile of infrared small targets, and augment it with a rotated pinwheel mask that adaptively aligns the kernel with target orientation via a straight-through estimator. Extensive experiments on IRSTD-1k, NUDT-SIRST, and SIRST-UAVB demonstrate consistent improvements in mIoUmIoU, PdP_d, and FaF_a over state-of-the-art methods. We release our anonymous code and pretrained models.

Hao Li, Man Fung Zhuo

Department of Electrical and Computer Engineering, University of Arizona, Tucson, USA

Infrared Small Target DetectionInfrared Object DetectionConvolutional Neural NetworksSemantic Segmentation
AskPDF
Apr 10, 2026

Benchmarking CNN- and Transformer-Based Models for Surgical Instrument Segmentation in Robotic-Assisted Surgery

Accurate segmentation of surgical instruments in robotic-assisted surgery is critical for enabling context-aware computer-assisted interventions, such as tool tracking, workflow analysis, and autonomous decision-making. In this study, we benchmark five deep learning architectures-UNet, UNet, DeepLabV3, Attention UNet, and SegFormer on the SAR-RARP50 dataset for multi-class semantic segmentation of surgical instruments in real-world radical prostatectomy videos. The models are trained with a compound loss function combining Cross Entropy and Dice loss to address class imbalance and capture fine object boundaries. Our experiments reveal that while convolutional models such as UNet and Attention UNet provide strong baseline performance, DeepLabV3 achieves results comparable to SegFormer, demonstrating the effectiveness of atrous convolution and multi-scale context aggregation in capturing complex surgical scenes. Transformer-based architectures like SegFormer further enhance global contextual understanding, leading to improved generalization across varying instrument appearances and surgical conditions. This work provides a comprehensive comparison and practical insights for selecting segmentation models in surgical AI applications, highlighting the trade-offs between convolutional and transformer-based approaches.

Sara Ameli

Medical Image SegmentationSemantic SegmentationSurgical RoboticsConvolutional Neural NetworksVision TransformerMedical Image Benchmarks
AskPDF
Apr 9, 2026

Scalable Neural Decoders for Practical Fault-Tolerant Quantum Computation

Quantum error correction (QEC) is essential for scalable quantum computing. However, it requires classical decoders that are fast and accurate enough to keep pace with quantum hardware. While quantum low-density parity-check codes have recently emerged as a promising route to efficient fault tolerance, current decoding algorithms do not allow one to realize the full potential of these codes in practical settings. Here, we introduce a convolutional neural network decoder that exploits the geometric structure of QEC codes, and use it to probe a novel "waterfall" regime of error suppression, demonstrating that the logical error rates required for large-scale fault-tolerant algorithms are attainable with modest code sizes at current physical error rates, and with latencies within the real-time budgets of several leading hardware platforms. For example, for the [144,12,12][144, 12, 12] Gross code, the decoder achieves logical error rates up to ∼17\sim 17x below existing decoders - reaching logical error rates ∼10−10\sim 10^{-10} at physical error p=0.1%p=0.1\% - with 3-5 orders of magnitude higher throughput. This decoder also produces well-calibrated confidence estimates that can significantly reduce the time overhead of repeat-until-success protocols. Taken together, these results suggest that the space-time costs associated with fault-tolerant quantum computation may be significantly lower than previously anticipated.

Andi Gu, J. Pablo Bonilla Ataides, Mikhail D. Lukin +1

Department of Physics, Harvard University, Cambridge, MA 02138, USA · Harvard Quantum Initiative, Harvard University, Cambridge, MA 02138, USA

Quantum Error CorrectionNeural DecodingConvolutional Neural Networks
AskPDF
Apr 9, 2026

Tensor-Augmented Convolutional Neural Networks: Enhancing Expressivity with Generic Tensor Kernels

Convolutional Neural Networks (CNNs) excel at extracting local features hierarchically, but their performance in capturing complex correlations hinges heavily on deep architectures, which are usually computationally demanding and difficult to interpret. To address these issues, we propose a physically-guided shallow model: tensor-augmented CNN (TACNN), which replaces conventional convolution kernels with generic tensors to enhance representational capacity. This choice is motivated by the fact that an order-NN tensor naturally encodes an arbitrary quantum superposition state in the Hilbert space of dimension dNd^N, where dd is the local physical dimension, thus offering substantially richer expressivity. Furthermore, in our design the convolution output of each layer becomes a multilinear form capable of capturing high-order feature correlations, thereby equipping a shallow multilayer architecture with an expressive power competitive to that of deep CNNs. On the Fashion-MNIST benchmark, TACNN demonstrates clear advantages over conventional CNNs, achieving remarkable accuracies with only a few layers. In particular, a TACNN with only two convolution layers attains a test accuracy of 93.7%\%, surpassing or matching considerably deeper models such as VGG-16 (93.5%\%) and GoogLeNet (93.7%\%). These findings highlight TACNN as a promising framework that strengthens model expressivity while preserving architectural simplicity, paving the way towards more interpretable and efficient deep learning models.

Chia-Wei Hsing, Wei-Lin Tu

blueqat Inc., 2-24-12-39F, Shibuya, Shibuya-ku, Tokyo 150-6139, Japan · Center for Quantum Science and Engineering, National Taiwan University, Taipei 10617, Taiwan · Graduate School of Science and Technology, Keio University, Yokohama, Kanagawa 223-8522, Japan +1

Convolutional Neural NetworksNeural Network ExpressivityShallow Neural NetworksImage Classification
AskPDF
Apr 9, 2026

FireSenseNet: A Dual-Branch CNN with Cross-Attentive Feature Interaction for Next-Day Wildfire Spread Prediction

Accurate prediction of next-day wildfire spread is critical for disaster response and resource allocation. Existing deep learning approaches typically concatenate heterogeneous geospatial inputs into a single tensor, ignoring the fundamental physical distinction between static fuel/terrain properties and dynamic meteorological conditions. We propose FireSenseNet, a dual-branch convolutional neural network equipped with a novel Cross-Attentive Feature Interaction Module (CAFIM) that explicitly models the spatially varying interaction between fuel and weather modalities through learnable attention gates at multiple encoder scales. Through a systematic comparison of seven architectures -- spanning pure CNNs, Vision Transformers, and hybrid designs -- on the Google Next-Day Wildfire Spread benchmark, we demonstrate that FireSenseNet achieves an F1 of 0.4176 and AUC-PR of 0.3435, outperforming all alternatives including a SegFormer with 3.8* more parameters (F1 = 0.3502). Ablation studies confirm that CAFIM provides a 7.1% relative F1 gain over naive concatenation, and channel-wise feature importance analysis reveals that the previous-day fire mask dominates prediction while wind speed acts as noise at the dataset's coarse temporal resolution. We further incorporate Monte Carlo Dropout for pixel-level uncertainty quantification and present a critical analysis showing that common evaluation shortcuts inflate reported F1 scores by over 44%.

Jinzhen Han, JinByeong Lee, Hak Han +2

Department of Civil, Architectural & Environment Engineering, Sungkyunkwan University, Suwon, South Korea · AI Urban Disaster Prevention Research Center, Advanced Institute of Convergence Technology (AICT), Suwon 16229, Republic of Korea · Department of Fire Safety Engineering, Jeonju University, Republic of Korea

Wildfire ForecastingConvolutional Neural NetworksCross-Attention
AskPDF
Apr 9, 2026

Adaptive Depth-converted-Scale Convolution for Self-supervised Monocular Depth Estimation

Self-supervised monocular depth estimation (MDE) has received increasing interests in the last few years. The objects in the scene, including the object size and relationship among different objects, are the main clues to extract the scene structure. However, previous works lack the explicit handling of the changing sizes of the object due to the change of its depth. Especially in a monocular video, the size of the same object is continuously changed, resulting in size and depth ambiguity. To address this problem, we propose a Depth-converted-Scale Convolution (DcSConv) enhanced monocular depth estimation framework, by incorporating the prior relationship between the object depth and object scale to extract features from appropriate scales of the convolution receptive field. The proposed DcSConv focuses on the adaptive scale of the convolution filter instead of the local deformation of its shape. It establishes that the scale of the convolution filter matters no less (or even more in the evaluated task) than its local deformation. Moreover, a Depth-converted-Scale aware Fusion (DcS-F) is developed to adaptively fuse the DcSConv features and the conventional convolution features. Our DcSConv enhanced monocular depth estimation framework can be applied on top of existing CNN based methods as a plug-and-play module to enhance the conventional convolution block. Extensive experiments with different baselines have been conducted on the KITTI benchmark and our method achieves the best results with an improvement up to 11.6% in terms of SqRel reduction. Ablation study also validates the effectiveness of each proposed module.

Yanbo Gao, Huibin Bai, Huasong Zhou +6

School of Software, Shandong University, Jinan 250100, China · Shandong University-WeiHai Research Institute of Industrial Technology, Weihai 264209, China · School of Control Science and Engineering, Shandong University, and Key Laboratory of Machine Intelligence and System Control, Ministry of Education, Jinan 250100, China +2

Monocular Depth EstimationConvolutional Neural NetworksMulti-Scale Feature Fusion
AskPDF
Apr 8, 2026

TeaLeafVision: An Explainable and Robust Deep Learning Framework for Tea Leaf Disease Classification

As the worlds second most consumed beverage after water, tea is not just a cultural staple but a global economic force of profound scale and influence. More than a mere drink, it represents a quiet negotiation between nature, culture, and the human desire for a moment of reflection. So, the precise identification and detection of tea leaf disease is crucial. With this goal, we have evaluated several Convolutional Neural Networks (CNN) models, among them three shows noticeable performance including DenseNet201, MobileNetV2, InceptionV3 on the teaLeafBD dataset. teaLeafBD dataset contains seven classes, six disease classes and one healthy class, collected under various field conditions reflecting real world challenges. Among the CNN models, DenseNet201 has achieved the highest test accuracy of 99%. In order to enhance the model reliability and interpretability, we have implemented Gradient weighted Class Activation Mapping (Grad CAM), occlusion sensitivity analysis and adversarial training techniques to increase the noise resistance of the model. Finally, we have developed a prototype in order to leverage the models capabilities on real life agriculture. This paper illustrates the deep learning models capabilities to classify the disease in real life tea leaf disease detection and management.

Rafi Ahamed, Sidratul Moon Nafsin, Md Abir Rahman +3

Dept. of CSE, East West University, Dhaka, Bangladesh · Dept. of BBA, East West University, Dhaka, Bangladesh

Plant Disease ClassificationConvolutional Neural NetworksExplainable Image Classification
AskPDF
Apr 8, 2026

Euclid Quick Data Release (Q1). AgileLens: A scalable CNN-based pipeline for strong gravitational lens identification

We present an end-to-end, iterative pipeline for efficient identification of strong galaxy--galaxy lensing systems, applied to the Euclid Q1 imaging data. Starting from VIS catalogues, we reject point sources, apply a magnitude cut (IE_E ≤\leq 24) on deflectors, and run a pixel-level artefact/noise filter to build 96 ×\times 96 pix cutouts; VIS+NISP colour composites are constructed with a VIS-anchored luminance scheme that preserves VIS morphology and NISP colour contrast. A VIS-only seed classifier supplies clear positives and typical impostors, from which we curate a morphology-balanced negative set and augment scarce positives. Among the six CNNs studied initially, a modified VGG16 (GlobalAveragePooling + 256/128 dense layers with the last nine layers trainable) performs best; the training set grows from 27 seed lenses (augmented to 1809) plus 2000 negatives to a colour dataset of 30,686 images. After three rounds of iterative fine-tuning, human grading of the top 4000 candidates ranked by the final model yields 441 Grade A/B candidate lensing systems, including 311 overlapping with the existing Q1 strong-lens catalogue, and 130 additional A/B candidates (9 As and 121 Bs) not previously reported. Independently, the model recovers 740 out of 905 (81.8%) candidate Q1 lenses within its top 20,000 predictions, considering off-centred samples. Candidates span IE_E ≃\simeq 17--24 AB mag (median 21.3 AB mag) and are redder in YE_E--HE_E than the parent population, consistent with massive early-type deflectors. Each training iteration required a week for a small team, and the approach easily scales to future Euclid releases; future work will calibrate the selection function via lens injection, extend recall through uncertainty-aware active learning, explore multi-scale or attention-based neural networks with fast post-hoc vetters that incorporate lens models into the classification.

Euclid Collaboration, X. Xu, R. Chen +308

Department of Physics \& Astronomy, University of California Irvine, Irvine CA 92697, USA · University of Southern California, 3551 Trousdale Parkway, Los Angeles, CA 90089, USA · Dipartimento di Fisica "Aldo Pontremoli", Università degli Studi di Milano, Via Celoria 16, 20133 Milano, Italy +165

Convolutional Neural NetworksImage Classification
AskPDF
Apr 6, 2026

YMIR: A new Benchmark Dataset and Model for Arabic Yemeni Music Genre Classification Using Convolutional Neural Networks

Automatic music genre classification is a major task in music information retrieval; however, most current benchmarks and models have been developed primarily for Western music, leaving culturally specific traditions underrepresented. In this paper, we introduce the Yemeni Music Information Retrieval (YMIR) dataset, which contains 1,475 carefully selected audio clips covering five traditional Yemeni genres: Sanaani, Hadhrami, Lahji, Tihami, and Adeni. The dataset was labeled by five Yemeni music experts following a clear and structured protocol, resulting in strong inter-annotator agreement (Fleiss kappa = 0.85). We also propose the Yemeni Music Classification Model (YMCM), a convolutional neural network (CNN)-based system designed to classify music genres from time-frequency features. Using a consistent preprocessing pipeline, we perform a systematic comparison across six experimental groups and five different architectures, resulting in a total of 30 experiments. Specifically, we evaluate several feature representations, including Mel-spectrograms, Chroma, FilterBank, and MFCCs with 13, 20, and 40 coefficients, and benchmark YMCM against standard models (AlexNet, VGG16, MobileNet, and a baseline CNN) under the same experimental conditions. The experimental findings reveal that YMCM is the most effective, achieving the highest accuracy of 98.8% with Mel-spectrogram features. The results also provide practical insights into the relationship between feature representation and model capacity. The findings establish YMIR as a useful benchmark and YMCM as a strong baseline for classifying Yemeni music genres.

Moeen AL-Makhlafi, Abdulrahman A. AlKannad, Eiad Almekhlafi +2

School of Artificial Intelligence, Xidian University, Xi’an, China. · Department of Information Science and Technology, Northwest University, Xi’an 710127, China.

Music Information RetrievalAudio ClassificationConvolutional Neural Networks
AskPDF
Apr 5, 2026

Measuring Robustness of Speech Recognition from MEG Signals Under Distribution Shift

This study investigates robust speech-related decoding from non-invasive MEG signals using the LibriBrain phoneme-classification benchmark from the 2025 PNPL competition. We compare residual convolutional neural networks (CNNs), an STFT-based CNN, and a CNN--Transformer hybrid, while also examining the effects of group averaging, label balancing, repeated grouping, normalization strategies, and data augmentation. Across our in-house implementations, preprocessing and data-configuration choices matter more than additional architectural complexity, among which instance normalization emerges as the most influential modification for generalization. The strongest of our own models, a CNN with group averaging, label balancing, repeated grouping, and instance normalization, achieves 60.95% F1-macro on the test split, compared with 39.53% for the plain CNN baseline. However, most of our models, without instance normalization, show substantial validation-to-test degradation, indicating that distribution shift induced by different normalization statistics is a major obstacle to generalization in our experiments. By contrast, MEGConformer maintains 64.09% F1-macro on both validation and test, and saliency-map analysis is qualitatively consistent with this contrast: weaker models exhibit more concentrated or repetitive phoneme-sensitive patterns across splits, whereas MEGConformer appears more distributed. Overall, the results suggest that improving the reliability of non-invasive phoneme decoding will likely require better handling of normalization-related distribution shift while also addressing the challenge of single-trial decoding.

Sheng-You Chien, Bo-Yi Mao, Yi-Ning Chang +1

Department of Computer Science, National Tsing-Hua University, Hsinchu, Taiwan

Distribution Shift RobustnessNeural DecodingConvolutional Neural Networks
AskPDF
Apr 4, 2026

SAGE-GAN: Towards Realistic and Robust Segmentation of Spatially Ordered Nanoparticles via Attention-Guided GANs

Precise analysis of nanoparticles for characterization in electron microscopy images is essential for advancing nanomaterial development. Yet it remains challenging due to the time-consuming nature of manual methods and the shortcomings of traditional automated segmentation techniques, especially when dealing with complex shapes and imaging artifacts. While conventional methods yield promising results, they depend on a large volume of labeled training data, which is both difficult to acquire and highly time-consuming to generate. In order to overcome these challenges, we have developed a two-step solution: Firstly, our system learns to segment the key features of nanoparticles from a dataset of real images using a self-attention driven U-Net architecture that focuses on important physical and morphological details while ignoring background features and noise. Secondly, this trained Attention U-Net is embedded in a cycle-consistent generative adversarial network (CycleGAN) framework, inspired by the cGAN-Seg model introduced by Abzargar et al. This integration allows for the creation of highly realistic synthetic electron microscopy image-mask pairs that naturally reflect the structural patterns learned by the Attention U-Net. Consequently, the model can accurately detect features in a diverse array of real-world nanoparticle images and autonomously augment the training dataset without requiring human input. Cycle consistency enforces a direct correspondence between synthetic images and ground-truth masks, ensuring realistic features, which is crucial for accurate segmentation training.

Anindya Pal, Varun Ajith, Saumik Bhattacharya +1

National Institute of Technology Durgapur, Department of Physics · Indian Institute of Technology Kharagpur

Image SegmentationMicroscopy Image AnalysisSynthetic Data AugmentationConvolutional Neural Networks
AskPDF
Apr 2, 2026

ROMAN: A Multiscale Routing Operator for Convolutional Time Series Models

We introduce ROMAN (ROuting Multiscale representAtioN), a deterministic operator for time series that maps temporal scale and coarse temporal position into an explicit channel structure while reducing sequence length. ROMAN builds an anti-aliased multiscale pyramid, extracts fixed-length windows from each scale, and stacks them as pseudochannels, yielding a compact representation on which standard convolutional classifiers can operate. In this way, ROMAN provides a simple mechanism to control the inductive bias of downstream models: it can reduce temporal invariance, make temporal pooling implicitly coarse-position-aware, and expose multiscale interactions through channel mixing, while often improving computational efficiency by shortening the processed time axis. We formally analyze the ROMAN operator and then evaluate it in two complementary ways by measuring its impact as a preprocessing step for four representative convolutional classifiers: MiniRocket, MultiRocket, a standard CNN-based classifier, and a fully convolutional network (FCN) classifier. First, we design synthetic time series classification tasks that isolate coarse position awareness, long-range correlation, multiscale interaction, and full positional invariance, showing that ROMAN behaves consistently with its intended mechanism and is most useful when class information depends on temporal structure that standard pooled convolution tends to suppress. Second, we benchmark the same models with and without ROMAN on long-sequence subsets of the UCR and UEA archives, showing that ROMAN provides a practically useful alternative representation whose effect on accuracy is task-dependent, but whose effect on efficiency is often favorable. Code is available at https://github.com/gon-uri/ROMAN

Gonzalo Uribarri

Department of Computer and Systems Sciences, Stockholm University

Time Series ClassificationMultiscale Time-Series ModelingConvolutional Neural Networks
AskPDF
Apr 2, 2026

Photonic convolutional neural network with pre-trained in situ training

Convolutional neural networks (CNNs) have transformed image processing, but the energy consumption and inference latency of electronic based implementations remain fundamental bottlenecks. These limitations have motivated the search for alternative hardware architectures beyond Complementary metal-oxide-semiconductor (CMOS) chips. Optical systems can perform linear matrix operations at the speed of light with extremely low energy dissipation, making them attractive for CNN acceleration. However, building a fully coherent photonic CNN that performs both linear and nonlinear operations and training it efficiently remains an open challenge. Here we present a fully photonic convolutional neural network (PCNN) that executes image classification in the optical domain, including convolution, max-pooling, nonlinear activation, and fully connected layers. The network achieves 94.49 percent accuracy on the MNIST dataset distributed across Mach Zehnder Interferometer (MZI) meshes, weighted Multimode Interferometer (MMI) trees, and a microring resonator based nonlinearity. A mathematically exact differentiable digital twin, enables backpropagation for ex situ pre training, reaches 97.45 percent digital accuracy. Trained phases are transferred one-to-one to the photonic hardware and refined via a gradient free algorithm that estimates the full gradient with only two forward passes. The architecture exhibits inherent robustness to non idealities, under the compound effect of propagation loss, MZI insertion loss, fabrication disorder, and thermal crosstalk. A bottom-up power analysis yields 10.83 W static chip consumption and 843 ns inference latency, translating to 220 to 330 times greater energy efficiency than state of the art electronic GPUs for single-image inference.

Saurabh Ranjan, Sonika Thakral, Amit Sehgal

Shaheed Sukhdev College of Business Studies, University of Delhi, New Delhi, Delhi 110085 · Hansraj College, University of Delhi, New Delhi, Delhi 110007

Photonic ComputingEfficient Neural Network InferenceConvolutional Neural NetworksImage Classification
AskPDF
Apr 1, 2026

Perceptual misalignment of texture representations in convolutional neural networks

Mathematical modeling of visual textures traces back to Julesz's intuition that texture perception in humans is based on local correlations between image features. An influential approach for texture analysis and generation generalizes this notion to linear correlations between the nonlinear features computed by convolutional neural networks (CNNs), compiled into Gram matrices. Given that CNNs are often used as models for the visual system, it is natural to ask whether such "texture representations" spontaneously align with the textures' perceptual content, and in particular whether those CNNs that are regarded as better models for the visual system also possess more human-like texture representations. Here we quantify the perceptual content captured by feature correlations computed for a diverse pool of CNNs, and we compare it to the models' perceptual alignment with the mammalian visual system as measured by Brain-Score. Surprisingly, we find that there is no connection between conventional measures of CNN quality as a model of the visual system and its alignment with human texture perception. We conclude that texture perception involves mechanisms that are distinct from those that are commonly modeled using approaches based on CNNs trained on object recognition, possibly depending on the integration of contextual information.

Ludovica de Paolis, Fabio Anselmi, Alessio Ansuini +1

Neuroscience area, International School for Advanced Studies (SISSA), Trieste, Italy · Department of Mathematics, Informatics and Geosciences, Università degli Studi di Trieste, Trieste, Italy · Department of Data Engineering, Area Science Park, Trieste, Italy

Convolutional Neural NetworksVisual Neuroscience
AskPDF
Mar 31, 2026

Central limit theorems for the outputs of fully convolutional neural networks with time series input

Deep learning is widely deployed for time series learning tasks such as classification and forecasting. Despite the empirical successes, only little theory has been developed so far in the time series context. In this work, we prove that if the network inputs are generated from short-range dependent linear processes, the outputs of fully convolutional neural networks (FCNs) with global average pooling (GAP) are asymptotically Gaussian and the limit is attained if the length of the observed time series tends to infinity. The proof leverages existing tools from the theoretical time series literature. Based on our theory, we propose a generalization of the GAP layer by considering a global weighted pooling step with slowly varying, learnable coefficients.

Annika Betken, Giorgio Micali, Johannes Schmidt-Hieber

University of Twente, Faculty of Electrical Engineering, Mathematics, and Computer Science (EEMCS), Drienerlolaan 5, 7522 NB Enschede, Netherlands

Convolutional Neural Networks
AskPDF
Mar 31, 2026

The Geometry of Polynomial Group Convolutional Neural Networks

We study polynomial group convolutional neural networks (PGCNNs) for an arbitrary finite group GG. In particular, we introduce a new mathematical framework for PGCNNs using the language of graded group algebras. This framework yields two natural parameterizations of the architecture, based on Hadamard and Kronecker products, related by a linear map. We compute the dimension of the associated neuromanifold, verifying that it depends only on the number of layers and the size of the group. Furthermore, we show the general fiber of both parameterizations is trivial up to the regular group action and rescaling. Hence both parametrization maps are identifiable.

Yacoub Hendi, Daniel Persson, Magdalena Larfors

Uppsala University · Chalmers University of Technology

Convolutional Neural NetworksPolynomial Neural NetworksEquivariant Neural NetworksParameter IdentifiabilityNeural Representation Geometry
AskPDF
Mar 30, 2026

Post-hoc Self-explanation of CNNs

Although standard Convolutional Neural Networks (CNNs) can be mathematically reinterpreted as Self-Explainable Models (SEMs), their built-in prototypes do not on their own accurately represent the data. Replacing the final linear layer with a kk-means-based classifier addresses this limitation without compromising performance. This work introduces a common formalization of kk-means-based post-hoc explanations for the classifier, the encoder's final output (B4), and combinations of intermediate feature activations. The latter approach leverages the spatial consistency of convolutional receptive fields to generate concept-based explanation maps, which are supported by gradient-free feature attribution maps. Empirical evaluation with a ResNet34 shows that using shallower, less compressed feature activations, such as those from the last three blocks (B234), results in a trade-off between semantic fidelity and a slight reduction in predictive performance.

Ahcène Boubekki, Line H. Clemmensen

Department of Mathematical Sciences, University of Copenhagen, Denmark

Neural Network InterpretabilityExplainable Image ClassificationConcept-Based ExplanationsConvolutional Neural Networks
AskPDF
Mar 30, 2026

Object Detection Based on Distributed Convolutional Neural Networks

Based on the Distributed Convolutional Neural Network(DisCNN), a straightforward object detection method is proposed. The modules of the output vector of a DisCNN with respect to a specific positive class are positively monotonic with the presence probabilities of the positive features. So, by identifying all high-scoring patches across all possible scales, the positive object can be detected by overlapping them to form a bounding box. The essential idea is that the object is detected by detecting its features on multiple scales, ranging from specific sub-features to abstract features composed of these sub-features. Training DisCNN requires only object-centered image data with positive and negative class labels. The detection process for multiple positive classes can be conducted in parallel to significantly accelerate it, and also faster for single-object detection because of its lightweight model architecture.

Liang Sun

Shandong University of Science and Technology, Jinan, 250031 P.R. China

Object DetectionConvolutional Neural Networks
AskPDF
Mar 27, 2026

TTE-CAM: Self-Explainable Class Activation Maps for Pretrained Black-Box CNNs

Convolutional neural networks (CNNs) achieve state-of-the-art performance in medical image analysis yet remain opaque, limiting adoption in high-stakes clinical settings. Existing approaches face a fundamental trade-off: post-hoc methods provide unfaithful approximate explanations, while inherently interpretable architectures are faithful but often sacrifice predictive performance. We introduce TTE-CAM, a test-time framework that bridges this gap by converting pretrained black-box CNNs into self-explainable models via a convolution-based replacement of their classification head, initialized from the original weights. The resulting model preserves black-box predictive performance while delivering built-in faithful explanations competitive with post-hoc methods, both qualitatively and quantitatively. The code is available at https://github.com/kdjoumessi/Test-Time-Explainability

Kerol Djoumessi, Philipp Berens

Hertie Institute for AI in Brain Health, University of Tübingen, Germany · Tübingen AI Center, University of Tübingen, Germany

Explainable Image ClassificationNeural Network InterpretabilityExplainable Medical Image AnalysisFeature AttributionConvolutional Neural Networks
AskPDF
Mar 26, 2026

End-to-end Feature Alignment: A Simple CNN with Intrinsic Class Attribution

We present Feature-Align CNN (FA-CNN), a prototype CNN architecture with intrinsic class attribution through end-to-end feature alignment. Our intuition is that the use of unordered operations such as Linear and Conv2D layers cause unnecessary shuffling and mixing of semantic concepts, thereby making raw feature maps difficult to understand. We introduce two new order preserving layers, the dampened skip connection, and the global average pooling classifier head. These layers force the model to maintain an end-to-end feature alignment from the raw input pixels all the way to final class logits. This end-to-end alignment enhances the interpretability of the model by allowing the raw feature maps to intrinsically exhibit class attribution. We prove theoretically that FA-CNN penultimate feature maps are identical to Grad-CAM saliency maps. Moreover, we prove that these feature maps slowly morph layer-by-layer over network depth, showing the evolution of features through network depth toward penultimate class activations. FA-CNN performs well on benchmark image classification datasets. Moreover, we compare the averaged FA-CNN raw feature maps against Grad-CAM and permutation methods in a percent pixels removed interpretability task. We conclude this work with a discussion and future, including limitations and extensions toward hybrid models.

Parniyan Farvardin, David Chapman

University of Miami

Neural Network InterpretabilityExplainable Image ClassificationConvolutional Neural NetworksFeature AttributionGradient-Based AttributionSaliency Map Evaluation
AskPDF
Mar 26, 2026

NERO-Net: A Neuroevolutionary Approach for the Design of Adversarially Robust CNNs

Neuroevolution automates the complex task of neural network design but often ignores the inherent adversarial fragility of evolved models which is a barrier to adoption in safety-critical scenarios. While robust training methods have received significant attention, the design of architectures exhibiting intrinsic robustness remains largely unexplored. In this paper, we propose NERO-Net, a neuroevolutionary approach to design convolutional neural networks better equipped to resist adversarial attacks. Our search strategy isolates architectural influence on robustness by avoiding adversarial training during the evolutionary loop. As such, our fitness function promotes candidates that, even trained with standard (non-robust) methods, achieve high post-attack accuracy without sacrificing the accuracy on clean samples. We assess NERO-Net on CIFAR-10 with a specific focus on L∞L_\infty-robustness. In particular, the fittest individual emerged from evolutionary search with 33% accuracy against FGSM, used as an efficient estimator for robustness during the search phase, while maintaining 87% clean accuracy. Further standard training of this individual boosted these metrics to 47% adversarial and 93% clean accuracy, suggesting inherent architectural robustness. Adversarial training brings the overall accuracy of the model up to 40% against AutoAttack.

Inês Valentim, Nuno Antunes, Nuno Lourenço

University of Coimbra, CISUC/LASI, DEI, Coimbra, Portugal

Adversarial RobustnessConvolutional Neural NetworksNeuroevolutionNeural Architecture SearchImage Classification
AskPDF
Mar 25, 2026

Reservoir-Based Graph Convolutional Networks

Message passing is a core mechanism in Graph Neural Networks (GNNs), enabling the iterative update of node embeddings by aggregating information from neighboring nodes. Graph Convolutional Networks (GCNs) exemplify this approach by adapting convolutional operations for graph structures, allowing features from adjacent nodes to be combined effectively. However, GCNs encounter challenges with complex or dynamic data. Capturing long-range dependencies often requires deeper layers, which not only increase computational costs but also lead to over-smoothing, where node embeddings become indistinguishable. To overcome these challenges, reservoir computing has been integrated into GNNs, leveraging iterative message-passing dynamics for stable information propagation without extensive parameter tuning. Despite its promise, existing reservoir-based models lack structured convolutional mechanisms, limiting their ability to accurately aggregate multi-hop neighborhood information. To address these limitations, we propose RGC-Net (Reservoir-based Graph Convolutional Network), which integrates reservoir dynamics with structured graph convolution. Key contributions include: (i) a reimagined convolutional framework with fixed-random reservoir weights and a leaky integrator to enhance feature retention; (ii) a robust, adaptable model for graph classification; and (iii) an RGC-Net-powered transformer for graph generation with application to dynamic brain connectivity. Extensive experiments show RGC-Net achieves state-of-the-art performance in classification and generative tasks, including brain graph evolution, with faster convergence and mitigated over-smoothing. Our source code is available at https://github.com/basiralab/RGC-Net.

Mayssa Soussia, Gita Ayu Salsabila, Mohamed Ali Mahjoub +1

National Engineering School of Sousse, University of Sousse, LATIS – Laboratory of Advanced Technology and Intelligent Systems, 4023, Sousse, Tunisia. · BASIRA Lab, Imperial-X and Department of Computing, Imperial College London, London, UK.

Graph Neural NetworksConvolutional Neural NetworksGraph ClassificationReservoir ComputingGraph Generation
AskPDF
Mar 24, 2026

An Explainable AI-Driven Framework for Automated Brain Tumor Segmentation Using an Attention-Enhanced U-Net

Computer-aided segmentation of brain tumors from MRI data is of crucial significance to clinical decision-making in diagnosis, treatment planning, and follow-up disease monitoring. Gliomas, owing to their high malignancy and heterogeneity, represent a very challenging task for accurate and reliable segmentation into intra-tumoral sub-regions. Manual segmentation is typically time-consuming and not reliable, which justifies the need for robust automated techniques.This research resolves this problem by leveraging the BraTS 2020 dataset, where we have labeled MRI scans of glioma patients with four significant classes: background/healthy tissue, necrotic/non-enhancing core, edema, and enhancing tumor. In this work, we present a new segmentation technique based on a U-Net model augmented with executed attention gates to focus on the most significant regions of images. To counter class imbalance, we employ manually designed loss functions like Dice Loss and Categorical Dice Loss, in conjunction with standard categorical cross-entropy. Other evaluation metrics, like sensitivity and specificity, were used to measure discriminability of the model between tumor classes. Besides, we introduce Grad-CAM-based explainable AI to enable visualizing attention regions and improve model interpretability, together with a smooth heatmap generation technique through Gaussian filtering. Our approach achieved superior performance with accuracy of 0.9919, Dice coefficient of 0.9901, mean IoU of 0.9873, sensitivity of 0.9908, and specificity of 0.9974. This study demonstrates that the use of attention mechanisms, personalized loss functions, and explainable AI significantly improves highly complex tumor structure segmentation precision in MRI scans, providing a reliable and explainable method for clinical applications.

MD Rashidul Islam, Bakary Gibba

School of Computing and Informatics Albukhary International University, 05200, Alor Setar, Malaysia

Brain Tumor SegmentationConvolutional Neural NetworksBraTSExplainable Medical Image Analysis
AskPDF
Mar 24, 2026

WaveSFNet: A Wavelet-Based Codec and Spatial--Frequency Dual-Domain Gating Network for Spatiotemporal Prediction

Spatiotemporal predictive learning aims to forecast future frames from historical observations in an unsupervised manner, and is critical to a wide range of applications. The key challenge is to model long-range dynamics while preserving high-frequency details for sharp multi-step predictions. Existing efficient recurrent-free frameworks typically rely on strided convolutions or pooling for sampling, which tends to discard textures and boundaries, while purely spatial operators often struggle to balance local interactions with global propagation. To address these issues, we propose WaveSFNet, an efficient framework that unifies a wavelet-based codec with a spatial--frequency dual-domain gated spatiotemporal translator. The wavelet-based codec preserves high-frequency subband cues during downsampling and reconstruction. Meanwhile, the translator first injects adjacent-frame differences to explicitly enhance dynamic information, and then performs dual-domain gated fusion between large-kernel spatial local modeling and frequency-domain global modulation, together with gated channel interaction for cross-channel feature exchange. Extensive experiments demonstrate that WaveSFNet achieves competitive prediction accuracy on Moving MNIST, TaxiBJ, and WeatherBench, while maintaining low computational complexity. Our code is available at https://github.com/fhjdqaq/WaveSFNet.

Xinyong Cai, Runming Xie, Hu Chen +1

College of Software Engineering, Sichuan University · College of Computer Science, Sichuan University · Sichuan University National Key Laboratory of Fundamental Science on Synthetic Vision

Spatiotemporal ForecastingConvolutional Neural NetworksFrequency-Domain Feature Learning
AskPDF
Mar 24, 2026

L-UNet: An LSTM Network for Remote Sensing Image Change Detection

Change detection of high-resolution remote sensing images is an important task in earth observation and was extensively investigated. Recently, deep learning has shown to be very successful in plenty of remote sensing tasks. The current deep learning-based change detection method is mainly based on conventional long short-term memory (Conv-LSTM), which does not have spatial characteristics. Since change detection is a process with both spatiality and temporality, it is necessary to propose an end-to-end spatiotemporal network. To achieve this, Conv-LSTM, an extension of the Conv-LSTM structure, is introduced. Since it shares similar spatial characteristics with the convolutional layer, L-UNet, which substitutes partial convolution layers of UNet-to-Conv-LSTM and Atrous L-UNet (AL-UNet), which further using Atrous structure to multiscale spatial information is proposed. Experiments on two data sets are conducted and the proposed methods show the advantages both in quantity and quality when compared with some other methods.

Shuting Sun, Lin Mu, Lizhe Wang +1

College of Marine Science and Technology, China University of Geosciences (CUG), Wuhan 430074, China · College of Life Sciences and Oceanography, Shenzhen University, Shenzhen 518060, China · Southern Marine Science and Engineering Guangdong Laboratory (Guangzhou), Guangzhou 511458, China +2

Remote Sensing Change DetectionU-NetConvolutional LSTMConvolutional Neural Networks
AskPDF
Mar 23, 2026

GradAttn: Replacing Fixed Residual Connections with Task-Modulated Attention Pathways

Deep ConvNets suffer from gradient signal degradation as network depth increases, limiting effective feature learning in complex architectures. ResNet addressed this through residual connections, but these fixed short circuits cannot adapt to varying input complexity or selectively emphasize task-relevant features across network hierarchies. This study introduces GradAttn, a variation of the residual approach in CNNs that replaces the fixed residual connections with attention-controlled gradient flow. By extracting multi-scale CNN features at different depths and regulating them through self-attention, GradAttn dynamically weights shallow texture features and deep semantic representations. For representational analysis, we evaluated three GradAttn variants across eight diverse datasets: from natural images and medical imaging to fashion recognition. The results demonstrate that GradAttn outperforms ResNet-18 on five of eight datasets, achieving up to +11.07% accuracy improvement on FashionMNIST while maintaining a comparable network size. Gradient flow analysis reveals that controlled instabilities, introduced by attention, often coincide with improved generalization, challenging the assumption that perfect stability is optimal. Furthermore, positional encoding's effectiveness turned out to be dataset-dependent, with CNN hierarchies frequently encoding sufficient spatial structure. These findings render attention mechanisms as enablers of learnable gradient control, offering a new way for adaptive representation learning in deep neural architectures.

Soudeep Ghoshal, Himanshu Buckchash

Kalinga Institute of Industrial Technology, Bhubaneswar, India · IMC University of Applied Sciences Krems, Krems, Austria

Convolutional Neural NetworksAttention Residual ConnectionsResidual LearningMulti-Scale Attention
AskPDF
Mar 23, 2026

SmaAT-QMix-UNet: A Parameter-Efficient Vector-Quantized UNet for Precipitation Nowcasting

Weather forecasting supports critical socioeconomic activities and complements environmental protection, yet operational Numerical Weather Prediction (NWP) systems remain computationally intensive, thus being inefficient for certain applications. Meanwhile, recent advances in deep data-driven models have demonstrated promising results in nowcasting tasks. This paper presents SmaAT-QMix-UNet, an enhanced variant of SmaAT-UNet that introduces two key innovations: a vector quantization (VQ) bottleneck at the encoder-decoder bridge, and mixed kernel depth-wise convolutions (MixConv) replacing selected encoder and decoder blocks. These enhancements both reduce the model's size and improve its nowcasting performance. We train and evaluate SmaAT-QMix-UNet on a Dutch radar precipitation dataset (2016-2019), predicting precipitation 30 minutes ahead. Three configurations are benchmarked: using only VQ, only MixConv, and the full SmaAT-QMix-UNet. Grad-CAM saliency maps highlight the regions influencing each nowcast, while a UMAP embedding of the codewords illustrates how the VQ layer clusters encoder outputs. The source code for SmaAT-QMix-UNet is publicly available on GitHub: https://github.com/nstavr04/MasterThesisSnellius.

Nikolas Stavrou, Siamak Mehrkanoon

Department of Information and Computing Sciences, Utrecht University, Utrecht, Netherlands

Precipitation NowcastingU-NetConvolutional Neural NetworksModel CompressionVector Quantization
AskPDF
Mar 23, 2026

SparseVoxelDet: Fully Sparse Voxel Networks for Efficient Event-Based Drone Detection

Event cameras excel at detecting small, fast drones, but today's detectors give away their key advantage: they convert the sparse event stream into dense grids and pay dense-processing cost on inputs that are almost entirely empty. We present SparseVoxelDet, to our knowledge the first coordinate-sparse 3D event voxel bounding-box detector: backbone, feature pyramid, temporal reduction, and detection head all operate directly on coordinate-indexed features, with no dense spatial grid at any stage. Building it exposed a hidden failure mode we name support inflation: an input filling a median 0.0652% of the voxel lattice inflates stage by stage until standard pyramid fusion leaves the detection head locally near-dense. We answer with two ideas. Expansion-free inverse-convolution fusion provably creates no active sites beyond the stored backbone supports, cutting head occupancy from a median 78.88% to 10.53%; quality-aligned supervision then recovers more accuracy than preserving sparsity costs. The payoff is measured, not assumed: executing the same trained network densely costs a median 27.5x the work and 4.65x the latency across 5,000 paired frames, with no frame cheaper dense, while the 6.22M-parameter detector reaches 87.01 AP50 on the FRED drone benchmark, ahead of matched dense controls, and holds its lead on the held-out test partition evaluated once. Sparsity, preserved by construction and supervised well, delivers the efficiency and the accuracy together.

Mohamad Yazan Sadoun, Sarah Sharif, Yaser Mike Banad

Inquire Lab, University of Oklahoma, Norman, OK, USA.

Event-Based Object DetectionEfficient Object DetectionEvent-Based VisionAerial Object DetectionConvolutional Neural Networks
AskPDF