Lightweight CNNs

CNN: Convolutional Neural Network

Follow this topic Ask about this topic

Lightweight CNN research seeks to retain useful accuracy while reducing parameters, computation, memory use, and inference time, especially on mobile and embedded hardware. Common approaches include depthwise-separable and grouped convolutions, compact encoder-decoder designs, pruning, quantization, knowledge distillation, and hardware-aware architecture search. These models are used for image classification, segmentation, restoration, and time-series tasks, with evaluation on both standard benchmarks and target devices. A central challenge is balancing accuracy and robustness with real deployment costs: fewer parameters or FLOPs do not always mean lower latency, and performance can drop when models meet varied data or hardware.

Latest papers

54 papers5 papers in the last four weeks, down 44% on the four weeks before. 0.0% of all new papers.

Jul 13, 2026

Towards Efficient Convolutional Neural Network for Embedded Hardware via Multi-Dimensional Pruning

In this paper, we propose TECO, a multi-dimensional pruning framework to collaboratively prune the three dimensions (depth, width, and resolution) of convolutional neural networks (CNNs) for better execution efficiency on embedded hardware. In TECO, we first introduce a two-stage importance evaluation framework, which efficiently and comprehensively evaluates each pruning unit according to both the local importance inside each dimension and the global importance across different dimensions. Based on the evaluation framework, we present a heuristic pruning algorithm to progressively prune the three dimensions of CNNs towards the optimal trade-off between accuracy and efficiency. Experiments on multiple benchmarks validate the advantages of TECO over existing state-of-the-art (SOTA) approaches. The code and pre-trained models are available at https://github.com/ntuliuteam/Teco.

Hao Kong, Di Liu, Xiangzhong Luo +5

School of Computer Science and Engineering, Nanyang Technological University, Singapore · HP-NTU Digital Manufacturing Corporate Lab, Nanyang Technological University, Singapore · Department of Computer Science, Norwegian University of Science and Technology, Trondheim, Norway. +1

Efficient Neural Network Inference Convolutional Neural Networks Edge ML Lightweight CNNs Neural Network Pruning

Jul 2, 2026

Do Newer Lightweight CNNs Perform Better Under Resource Constraints? A Controlled Multigenerational Study of Architecture, Initialization, Training Budget, and Efficiency

Newer lightweight convolutional neural networks are often presented as improving predictive performance and deployment efficiency, but such claims require controlled evaluation. This study compares nine lightweight CNN model packages across CIFAR-10, CIFAR-100, and Tiny ImageNet under a shared downstream protocol. We report top-1 accuracy, macro F1, top-5 accuracy, parameter count, FP32 storage, GMACs, batch-size-1 latency on an NVIDIA L4 and AMD Ryzen 5 5500U CPU, peak PyTorch CUDA allocated tensor memory, and point estimate Pareto frontiers. EfficientNetV2-S achieves the highest observed top-1 accuracy on CIFAR-10 and CIFAR-100 at 97.57% and 86.98%, while RepViT-M1.0 leads Tiny ImageNet at 79.87%. EfficientNet-B0 remains within 0.22, 0.85, and 1.79 percentage points of the best result on the three datasets while using approximately 79% fewer parameters and 86% fewer GMACs than EfficientNetV2-S. It also appears on every evaluated accuracy and resource Pareto frontier, making it the most consistently competitive intermediate-budget option. MobileNetV3-Small has the lowest GMAC count, is the fastest model under both CPU thread settings, and records higher observed accuracy than MobileNetV4-Conv-S on all three datasets. Under random initialization, it leads MobileNetV4-Conv-S by 2.55, 1.76, and 0.99 points, with paired test-set intervals excluding zero for the fixed trained models. EfficientNet-B0 remains 3.29, 10.10, and 17.54 points below its pretrained counterpart after 100 epochs of scratch training, despite requiring about five times the recorded training time. SqueezeNet1.1 has the fewest parameters and lowest peak CUDA allocation, but substantially weaker accuracy. Latency rankings differ sharply between the L4 and CPU environments, showing that GMACs alone do not predict measured inference performance. Overall, newer designs provide selective rather than universal gains

Tasnim Shahriar

Independent Researcher

Efficient Neural Network Inference Convolutional Neural Networks Lightweight CNNs Image Classification Lightweight Neural Networks

Jun 29, 2026

Real-Time Underwater Image Enhancement via Frequency-Guided Dual-Path Attention

Real-time underwater image enhancement (UIE) is crucial for mobile underwater photography and autonomous robotic systems, where practical deployment typically requires low latency and compact models under constrained computational resources. Recent ultra-lightweight CNNs based on structural re-parameterization meet these constraints but operate purely in the spatial domain, ignoring the frequency-sensitive nature of underwater degradation. To address this, we propose a lightweight UIE framework that integrates two key components: a Multi-Branch Reparameterizable Convolution with Fixed DCT Priors (MBRConv-DCT) that injects structured directional frequency priors during training, and a Frequency-Guided Dual-Path Attention (FGDPA) module that fuses spatial and spectral cues via a dual-path design for adaptive feature modulation. Both components are fully compatible with structural re-parameterization: the convolution branch introduces zero additional inference cost after re-parameterization, while the attention module incurs only a minimal computational overhead. Experiments show our model achieves state-of-the-art performance with only 4.23K parameters and 600+ FPS, outperforming much larger methods in both quantitative metrics and visual quality. Code is available at https://github.com/LethyZhang/FGDPA.

Leshen Zhang, Ao Li, Ce Zhu

Glasgow College, UESTC, Chengdu, China · University of Glasgow, Glasgow, UK · School of Information and Communication Engineering, UESTC, Chengdu, China

Image Enhancement Underwater Image Enhancement Frequency-Domain Image Processing Convolutional Neural Networks Lightweight CNNs

Jun 15, 2026

An affordable hardware-aware neural architecture search for deploying convolutional neural networks on ultra-low-power computing platforms

Hardware-aware neural architecture search (HW-NAS) allows the integration of Convolutional Neural Networks (CNNs) in microcontrollers devices by automatically designing neural architectures that can fit prearranged hardware constraints. However, state-of-the-art HW-NAS target high-performance microcontrollers, whose power consumption does not meet sensing nodes requirements. This work presents a HW-NAS generating tiny CNNs that can run on ultra-low-power microcontrollers, featuring a lightweight search procedure enabling its execution even on embedded devices. Empirical results on three well-known benchmarks for tiny computer vision proved that the proposed HW-NAS was able to generate tiny CNNs while preserving state-of-the-art classification accuracy.

Andrea Mattia Garavagno, Edoardo Ragusa, Antonio Frisoli +1

Dept. of Electrical, Electronic, Telecommunications Engineering and Naval Architecture (DITEN), University of Genoa, Genoa, Italy · Department of Excellence in Robotics & AI and Institute of Mechanical Intelligence, Scuola Superiore Sant’Anna, 56127 Pisa, Italy

Efficient Neural Network Inference Tiny ML Hardware-Aware NAS Convolutional Neural Networks Edge ML Lightweight CNNs+1

May 10, 2026

XTinyU-Net: Training-Free U-Net Scaling via Initialization-Time Sensitivity

While U-Net architectures remain the gold standard for medical image segmentation, their deployment in resource-constrained environments demands aggressive model compression. However, finding an optimally efficient configuration is computationally prohibitive, typically requiring exhaustive train-and-evaluate cycles to find the smallest model that maintains peak performance. In this paper, we introduce a training-free selection framework to automatically identify ultralightweight, dataset-specific U-Net configurations directly at initialization. We observe that systematically scaling down U-Net channel width induces a sharp transition from a stable performance plateau to representational capacity collapse. To pinpoint this boundary without training, we propose a Jacobian-based sensitivity metric that scores discrete, width-capped U-Net variants using a small set of unlabeled images. By analyzing the total variation of this sensitivity curve, we isolate the smallest stable configuration, which we denote as XTinyU-Net. Evaluated across six diverse medical datasets within the nnU-Net framework, XTinyU-Net achieves segmentation accuracy comparable to the heavy nnU-Net baseline with 400x-1600x fewer parameters, and outperforms contemporary lightweight architectures while utilizing 5x-72x fewer parameters. Code is publicly accessible on https://github.com/alvinkimbowa/nntinyunet.git.

Alvin Kimbowa, Moein Heidari, David Liu +1

School of Biomedical Engineering, The University of British Columbia, Vancouver, Canada · Department of Radiology, The University of British Columbia, Vancouver, Canada · Department of Medicine, The University of British Columbia, Vancouver, Canada

Model Compression U-Net Medical Image Segmentation Convolutional Neural Networks Neural Architecture Search Lightweight CNNs

Apr 30, 2026

Robust Lightweight Crack Classification for Real-Time UAV Bridge Inspection

With the widespread application of Unmanned Aerial Vehicles (UAVs) in bridge structural health monitoring, deep learning-based automatic crack detection has become a major research focus. However, practical UAV inspections still face four key challenges: weak crack features, degraded imaging conditions, severe class imbalance, and limited computational resources for practical UAV inspection workflows. To address these issues, this paper proposes a unified lightweight convolutional neural network framework composed of four synergistic components: a lightweight backbone network, a Convolutional Block Attention Module (CBAM) for channel and spatial enhancement, a directed robust augmentation strategy based on inspection-scene priors, and Focal Loss for hard-sample learning under class imbalance. Experiments on the SDNET2018 bridge deck dataset show that the proposed method achieves an inference speed of 825 FPS with only 11.21M parameters and 1.82G FLOPs. Compared with the baseline model, the complete framework improves the F1-score by 2.51% and recall by 3.95%. In addition, Grad-CAM visualizations indicate that the introduced attention module shifts the model's focus from scattered regions to precise tracking along crack trajectories. Overall, this study achieves a strong balance among accuracy, speed, and robustness, providing a practical solution for ground-station assisted real-time deployment in UAV bridge inspections. The source code is available at: https://github.com/skylynf/AttXNet .

Wei Li, Haisheng Li, Weijie Li +3

Bay Area Super Bridge Maintenance Technology Center, Guangdong Provincial Highway Construction Co., Ltd., Guangdong, China · Guangdong AIHISUN Technology Co., Ltd., Guangdong, China

Convolutional Neural Networks Lightweight CNNs Structural Health Monitoring

Apr 28, 2026

A Light Weight Multi-Features-View Convolution Neural Network For Plant Disease Identification

Agriculture is a key sector of the economies of developing countries. It serves as a primary source of income and employment for rural populations. However, each year, a large portion of crops is wasted because of pests and diseases. Well-timed prediction of plant diseases is crucial to sustainable, high-quality agricultural production. Detection of plant diseases through conventional methods is both labour-intensive and time-consuming. Researchers have developed image classification based automated techniques for this purpose. Most accurate methods are based on deep convolutional neural networks, which are computationally intensive, with many layers and millions of trainable parameters. In resource-constrained settings, especially in rural areas, it is difficult to deploy deep convolutional neural network models for efficient plant disease identification. To address these issues, an efficient and light-weight Multi-View Convolutional Neural Network is proposed. These additional features aid the proposed model to identify the plant diseases accurately and efficiently with less number of parameters. The proposed model is tested on a benchmark Plantvillage dataset and achieves an improvement of

2.9\%

in classification accuracy compared to the baseline convolutional neural network model, which was trained only on Red, Green, and Blue (RGB) plant images. Compared with state-of-the-art deep convolutional neural network models, the proposed model is less computationally expensive and achieves comparable accuracy for plant disease identification on the PlantVillage dataset.

Muhammad Kaleem Ullah Khan

COMSATS University Islamabad, Pakistan

Efficient Neural Network Inference Plant Disease Classification Multi-View Learning Convolutional Neural Networks Lightweight CNNs

Apr 23, 2026

Vision-Based Lane Following and Traffic Sign Recognition for Resource-Constrained Autonomous Vehicles

Autonomous vehicles (AVs) rely on real-time perception systems to understand road environments and ensure safe navigation. However, implementing reliable perception algorithms on resource-constrained embedded platforms remains challenging due to limited computational resources. This paper presents a lightweight vision-based framework that integrates lane detection, lane tracking, and traffic sign recognition for embedded autonomous vehicles. A computationally efficient threshold-based lane segmentation method combined with perspective transformation and histogram-based curvature estimation is used for robust lane tracking under varying illumination conditions. A rule-based steering controller generates steering commands to maintain stable vehicle navigation. For traffic sign recognition, two lightweight convolutional neural networks (CNNs), EfficientNet-B0 and MobileNetV2, are evaluated using a custom dataset captured from the vehicle's onboard camera. Experimental results show that the system achieves real-time performance while maintaining accurate lane tracking with only 3.16% maximum offset RMSE. EfficientNet-B0 achieves a high offline classification accuracy of 98.77% on the test dataset, while achieving 90% accuracy during real-time on-device deployment, outperforming MobileNetV2 in both settings. MobileNetV2, however, offers slightly faster inference and lower computational cost. These results highlight the effectiveness of lightweight vision-based perception pipelines for resource-constrained autonomous driving applications.

Md Tanjemul Islam, Md Rafiul Kabir

Central Michigan University, Mount Pleasant, MI, USA

Visual Navigation Autonomous Driving Perception Convolutional Neural Networks Lightweight CNNs

Apr 15, 2026

A Resource-Efficient Hybrid CNN-LSTM network for image-based bean leaf disease classification

Accurate and resource-efficient automated diagnosis is a cornerstone of modern agricultural expert systems. While Convolutional Neural Networks (CNNs) have established benchmarks in plant pathology, their ability to capture long-range spatial dependencies is often limited by standard pooling layers, and their high memory footprint hinders deployment on portable devices. This paper proposes a lightweight hybrid CNN-LSTM system for bean leaf disease classification. By integrating an LSTM layer to model the spatial-sequential relationships within feature maps, our hybrid architecture achieves a 94.38% accuracy while maintaining an exceptionally small footprint of 1.86 MB; a 70% reduction in size compared to traditional CNN-based systems. Furthermore, we provide a systematic evaluation of image augmentation strategies, demonstrating that tailored transformations are superior to generic combinations for maintaining the integrity of diagnostic patterns. Results on the

\textit{ibean}

dataset confirm that the proposed system achieves state-of-the-art F1 scores of 99.22% with EfficientNet-B7+LSTM, providing a robust and scalable framework for real-time agricultural decision support in resource-constrained environments. The code and augmented datasets used in this study are publicly available on this Github repo.

Hye Jin Rhee, Joseph Damilola Akinyemi

University of York, Heslington, York, YO10 5DD, United Kingdom

Plant Disease Classification Lightweight CNNs Efficient Neural Network Inference

Apr 13, 2026

A Compact and Efficient 1.251 Million Parameter Machine Learning CNN Model PD36-C for Plant Disease Detection: A Case Study

Deep learning has markedly advanced image based plant disease diagnosis as improved hardware and dataset quality have enabled increasingly accurate neural network models. This paper presents PD36 C, a compact convolutional neural network (1,250,694 parameters and 4.77 MB) for plant disease classification. Trained with TensorFlow Keras on the New Plant Diseases Dataset (87k images, 38 classes), PD36 C is designed for robustness and edge deployability, complemented by a Qt for Python desktop application that offers an intuitive GUI and offline inference on commodity hardware. Across experiments, training accuracy reached 0.99697 by epoch 30, and average test accuracy was 0.9953 across 38 classes. Per class performance is uniformly high; on the lower end, Corn (maize) Cercospora leaf spot achieved precision around 0.9777 and recall around 0.9634, indicating occasional confusion with visually similar categories, while on the upper end numerous classes including Apple Black rot, Cedar apple rust, Blueberry healthy, Cherry Powdery mildew, Cherry healthy, and all four grape categories achieved perfect precision 1.00 and recall of 1.00, indicating no false positives and strong coverage. These results show that with a well curated dataset and careful architectural design, small CNNs can achieve competitive accuracy compared with recent baselines while remaining practical for edge scenarios. We also note typical constraints such as adverse weather, low quality imagery, and leaves exhibiting multiple concurrent diseases that can degrade performance and warrant future work on domain robustness. Overall, PD36 C and its application pipeline contribute a field ready, efficient solution for AI assisted plant disease detection in smart agriculture.

Shkelqim Sherifi

Computer Science Independent Researcher Tetove, R.N.Macedonia

Plant Disease Classification Lightweight CNNs Edge ML

Apr 1, 2026

OkanNet: A Lightweight Deep Learning Architecture for Classification of Brain Tumor from MRI Images

Medical imaging techniques, especially Magnetic Resonance Imaging (MRI), are accepted as the gold standard in the diagnosis and treatment planning of neurological diseases. However, the manual analysis of MRI images is a time-consuming process for radiologists and is prone to human error due to fatigue. In this study, two different Deep Learning approaches were developed and analyzed comparatively for the automatic detection and classification of brain tumors (Glioma, Meningioma, Pituitary, and No Tumor). In the first approach, a custom Convolutional Neural Network (CNN) architecture named "OkanNet", which has a low computational cost and fast training time, was designed from scratch. In the second approach, the Transfer Learning method was applied using the 50-layer ResNet-50 [1] architecture, pre-trained on the ImageNet dataset. In experiments conducted on an extended dataset compiled by Masoud Nickparvar containing a total of

7,023

MRI images, the Transfer Learning-based ResNet-50 model exhibited superior classification performance, achieving

96.49\%

Accuracy and

0.963

Precision. In contrast, the custom OkanNet architecture reached an accuracy rate of

88.10\%

; however, it proved to be a strong alternative for mobile and embedded systems with limited computational power by yielding results approximately

3.2

times faster (

311

seconds) than ResNet-50 in terms of training time. This study demonstrates the trade-off between model depth and computational efficiency in medical image analysis through experimental data.

Okan Uçar, Murat Kurt

Graduate School of Natural and Applied Sciences Department of Computer Engineering Ege University Izmir, Turkey · International Computer Institute Ege University Izmir, Turkey

Brain Tumor Classification Medical Image Classification Lightweight CNNs

Mar 27, 2026

On-Device Super Resolution Imaging Using Low-Cost SPAD Array and Embedded Lightweight Deep Learning

This work presents a lightweight super-resolution (LiteSR) neural network for depth and intensity images acquired from a consumer-grade single-photon avalanche diode (SPAD) array with a 48x32 spatial resolution. The proposed framework reconstructs high-resolution (HR) images of size 256x256. Both synthetic and real datasets are used for performance evaluation. Extensive quantitative metrics demonstrate high reconstruction fidelity on synthetic datasets, while experiments on real indoor and outdoor measurements further confirm the robustness of the proposed approach. Moreover, the SPAD sensor is interfaced with an Arduino UNO Q microcontroller, which receives low-resolution (LR) depth and intensity images and feeds them into a compressed, pre-trained deep learning (DL) model, enabling real-time SR video streaming. In addition to the 256x256 setting, a range of target HR resolutions is evaluated to determine the maximum achievable upscaling resolution (512x512) with LiteSR, including scenarios with noise-corrupted LR inputs. The proposed LiteSR-embedded system co-design provides a scalable, cost-effective solution to enhance the spatial resolution of current consumer-grade SPAD arrays to meet HR imaging requirements.

Zhenya Zang, Xingda Li, David Day Uei Li

Department of Biomedical Engineering, University of Strathclyde, 16 Richmond Street, Glasgow, G1 1XQ, United Kingdom

Image Super-Resolution Computational Imaging Lightweight CNNs On-Device Inference

Mar 27, 2026

CPUBone: Efficient Vision Backbone Design for Devices with Low Parallelization Capabilities

Recent research on vision backbone architectures has predominantly focused on optimizing efficiency for hardware platforms with high parallel processing capabilities. This category increasingly includes embedded systems such as mobile phones and embedded AI accelerator modules. In contrast, CPUs do not have the possibility to parallelize operations in the same manner, wherefore models benefit from a specific design philosophy that balances amount of operations (MACs) and hardware-efficient execution by having high MACs per second (MACpS). In pursuit of this, we investigate two modifications to standard convolutions, aimed at reducing computational cost: grouping convolutions and reducing kernel sizes. While both adaptations substantially decrease the total number of MACs required for inference, sustaining low latency necessitates preserving hardware-efficiency. Our experiments across diverse CPU devices confirm that these adaptations successfully retain high hardware-efficiency on CPUs. Based on these insights, we introduce CPUBone, a new family of vision backbone models optimized for CPU-based inference. CPUBone achieves state-of-the-art Speed-Accuracy Trade-offs (SATs) across a wide range of CPU devices and effectively transfers its efficiency to downstream tasks such as object detection and semantic segmentation. Models and code are available at https://github.com/altair199797/CPUBone.

Moritz Nottebaum, Matteo Dunnhofer, Christian Micheloni

University of Udine, Italy · York University, Canada

Efficient Neural Network Inference Lightweight CNNs

Mar 19, 2026

VeloxNet: Efficient Spatial Gating for Lightweight Embedded Image Classification

Deploying deep learning models on embedded devices for tasks such as aerial disaster monitoring and infrastructure inspection requires architectures that balance accuracy with strict constraints on model size, memory, and latency. This paper introduces VeloxNet, a lightweight CNN architecture that replaces SqueezeNet's fire modules with gated multi-layer perceptron (gMLP) blocks for embedded image classification. Each gMLP block uses a spatial gating unit (SGU) that applies learned spatial projections and multiplicative gating, enabling the network to capture spatial dependencies across the full feature map in a single layer. Unlike fire modules, which are limited to local receptive fields defined by small convolutional kernels, the SGU provides global spatial modeling at each layer with fewer parameters. We evaluate VeloxNet on three aerial image datasets: the Aerial Image Database for Emergency Response (AIDER), the Comprehensive Disaster Dataset (CDD), and the Levee Defect Dataset (LDD), comparing against eleven baselines including MobileNet variants, ShuffleNet, EfficientNet, and recent vision transformers. VeloxNet reduces the parameter count by 46.1% relative to SqueezeNet (from 740,970 to 399,366) while improving weighted F1 scores by 6.32% on AIDER, 30.83% on CDD, and 2.51% on LDD. These results demonstrate that substituting local convolutional modules with spatial gating blocks can improve both classification accuracy and parameter efficiency for resource-constrained deployment. The source code will be made publicly available upon acceptance of the paper.

Md Meftahul Ferdaus, Elias Ioup, Mahdi Abdelguerfi +4

Canizaro Livingston Gulf States Center for Environmental Informatics, the University of New Orleans, New Orleans, USA · Center for Geospatial Sciences, Naval Research Laboratory, Stennis Space Center, Hancock County, Mississippi, USA · US Army Corps of Engineers, Engineer Research and Development Center, Vicksburg, Mississippi, USA

Image Classification Lightweight CNNs Edge Inference Multilayer Perceptrons

Mar 12, 2026

UCAN: Unified Convolutional Attention Network for Expansive Receptive Fields in Lightweight Super-Resolution

Hybrid CNN-Transformer architectures achieve strong results in image super-resolution, but scaling attention windows or convolution kernels significantly increases computational cost, limiting deployment on resource-constrained devices. We present UCAN, a lightweight network that unifies convolution and attention to expand the effective receptive field efficiently. UCAN combines window-based spatial attention with a Hedgehog Attention mechanism to model both local texture and long-range dependencies, and introduces a distillation-based large-kernel module to preserve high-frequency structure without heavy computation. In addition, we employ cross-layer parameter sharing to further reduce complexity. On Manga109 (

4\times

), UCAN-L achieves 31.63 dB PSNR with only 48.4G MACs, surpassing recent lightweight models. On BSDS100, UCAN attains 27.79 dB, outperforming methods with significantly larger models. Extensive experiments show that UCAN achieves a superior trade-off between accuracy, efficiency, and scalability, making it well-suited for practical high-resolution image restoration.

Cao Thien Tan, Phan Thi Thu Trang, Do Nghiem Duc +3

Ho Chi Minh City Open University · AI Tech Lab, Ho Chi Minh City University of Technology · Code Mely AI Research Team +3

Image Super-Resolution Lightweight CNNs Hybrid CNN-Transformer Architectures Hybrid Attention

Mar 6, 2026

XMACNet: An Explainable Lightweight Attention based CNN with Multi Modal Fusion for Chili Disease Classification

Plant disease classification via imaging is a critical task in precision agriculture. We propose XMACNet, a novel light-weight Convolutional Neural Network (CNN) that integrates self-attention and multi-modal fusion of visible imagery and vegetation indices for chili disease detection. XMACNet uses an EfficientNetV2S backbone enhanced by a self-attention module and a fusion branch that processes both RGB images and computed vegetation index maps (NDVI, NPCI, MCARI). We curated a new dataset of 12,000 chili leaf images across six classes (five disease types plus healthy), augmented synthetically via StyleGAN to mitigate data scarcity. Trained on this dataset, XMACNet achieves high accuracy, F1-score, and AUC, outperforming baseline models such as ResNet-50, MobileNetV2, and a Swin Transformer variant. Crucially, XMACNet is explainable: we use Grad-CAM++ and SHAP to visualize and quantify the models focus on disease features. The models compact size and fast inference make it suitable for edge deployment in real-world farming scenarios.

Tapon Kumer Ray, Rajkumar Y, Shalini R +3

Student, Vellore Institute of Technology, Amaravati, Andhra Pradesh, India. · Assistant Professor, Vellore Institute of Technology, Amaravati, Andhra Pradesh, India. · Student, Angel College of Engineering and Technology, Tiruppur, Tamilnadu, India +2

Plant Disease Classification Lightweight CNNs Multimodal Classification Explainable Image Classification

Feb 28, 2026

A Parameter-efficient Convolutional Approach for Camouflaged Weed Detection in Multispectral Aerial Imagery

We introduce FCBNet, an efficient model designed for camouflaged weed detection. The architecture is based on a fully frozen ConvNeXt backbone, the proposed Feature Correction Block (FCB), which leverages efficient convolutions for feature refinement, and a lightweight decoder. FCBNet is evaluated on the WeedBananaCOD and WeedMap datasets under both RGB and multispectral modalities, showing that FCBNet outperforms models such as U-Net, DeepLabV3+, SK-U-Net, SegFormer, and WeedSense in terms of mIoU, exceeding 85%, while also achieving superior computational efficiency, requiring only 0.06 to 0.2 hours for training. Furthermore, the frozen backbone strategy reduces the number of trainable parameters by more than 90%, significantly lowering memory requirements. Code available at: https://github.com/Leo-Thomas/fcbnet

Leo Thomas Ramos, Angel D. Sappa

Computer Vision Center · Universitat Aut`onoma de Barcelona · ESPOL Polytechnic University

Weed Detection Camouflaged Object Detection Agricultural Remote Sensing Lightweight CNNs

Feb 27, 2026

ULW-SleepNet: An Ultra-Lightweight Network for Multimodal Sleep Stage Scoring

Automatic sleep stage scoring is crucial for the diagnosis and treatment of sleep disorders. Although deep learning models have advanced the field, many existing models are computationally demanding and designed for single-channel electroencephalography (EEG), limiting their practicality for multimodal polysomnography (PSG) data. To overcome this, we propose ULW-SleepNet, an ultra-lightweight multimodal sleep stage scoring framework that efficiently integrates information from multiple physiological signals. ULW-SleepNet incorporates a novel Dual-Stream Separable Convolution (DSSC) Block, depthwise separable convolutions, channel-wise parameter sharing, and global average pooling to reduce computational overhead while maintaining competitive accuracy. Evaluated on the Sleep-EDF-20 and Sleep-EDF-78 datasets, ULW-SleepNet achieves accuracies of 86.9% and 81.4%, respectively, with only 13.3K parameters and 7.89M FLOPs. Compared to state-of-the-art methods, our model reduces parameters by up to 98.6% with only marginal performance loss, demonstrating its strong potential for real-time sleep monitoring on wearable and IoT devices. The source code for this study is publicly available at https://github.com/wzw999/ULW-SLEEPNET.

Zhaowen Wang, Dongdong Zhou, Qi Xu +3

School of Computer Science and Technology, Dalian University of Technology, Dalian, China · Faculty of Information Technology, University of Jyväskylä, Jyväskylä, Finland · Key Laboratory of Social Computing and Cognitive Intelligence, Ministry of Education, Dalian, China +3

Depthwise Separable Convolution Sleep Stage Classification Lightweight CNNs Convolutional Neural Networks

Feb 24, 2026

FLIM Networks with Bag of Feature Points

Convolutional networks require extensive image annotation, which can be costly and time-consuming. Feature Learning from Image Markers (FLIM) tackles this challenge by estimating encoder filters (i.e., kernel weights) from user-drawn markers on discriminative regions of a few representative images without traditional optimization. Such an encoder combined with an adaptive decoder comprises a FLIM network fully trained without backpropagation. Prior research has demonstrated their effectiveness in Salient Object Detection (SOD), being significantly lighter than existing lightweight models. This study revisits FLIM SOD and introduces FLIM-Bag of Feature Points (FLIM-BoFP), a considerably faster filter estimation method. The previous approach, FLIM-Cluster, derives filters through patch clustering at each encoder's block, leading to computational overhead and reduced control over filter locations. FLIM-BoFP streamlines this process by performing a single clustering at the input block, creating a bag of feature points, and defining filters directly from mapped feature points across all blocks. The paper evaluates the benefits in efficiency, effectiveness, and generalization of FLIM-BoFP compared to FLIM-Cluster and other state-of-the-art baselines for parasite detection in optical microscopy images.

João Deltregia Martinelli, Marcelo Luis Rodrigues Filho, Felipe Crispim da Rocha Salvagnini +3

Institute of Computing UNICAMP Campinas, Brazil · School of Computer Science University of Sheffield Sheffield, United Kingdom

Salient Object Detection Lightweight CNNs Microscopy Image Analysis

Feb 24, 2026

PFGNet: A Fully Convolutional Frequency-Guided Peripheral Gating Network for Efficient Spatiotemporal Predictive Learning

Spatiotemporal predictive learning (STPL) aims to forecast future frames from past observations and is essential across a wide range of applications. Compared with recurrent or hybrid architectures, pure convolutional models offer superior efficiency and full parallelism, yet their fixed receptive fields limit their ability to adaptively capture spatially varying motion patterns. Inspired by biological center-surround organization and frequency-selective signal processing, we propose PFGNet, a fully convolutional framework that dynamically modulates receptive fields through pixel-wise frequency-guided gating. The core Peripheral Frequency Gating (PFG) block extracts localized spectral cues and adaptively fuses multi-scale large-kernel peripheral responses with learnable center suppression, effectively forming spatially adaptive band-pass filters. To maintain efficiency, all large kernels are decomposed into separable 1D convolutions (

1 \times k

followed by

k \times 1

), reducing per-channel computational cost from

O(k^2)

to

O(2k)

. PFGNet enables structure-aware spatiotemporal modeling without recurrence or attention. Experiments on Moving MNIST, TaxiBJ, Human3.6M, and KTH show that PFGNet delivers SOTA or near-SOTA forecasting performance with substantially fewer parameters and FLOPs. Our code is available at https://github.com/fhjdqaq/PFGNet.

Xinyong Cai, Changbin Sun, Yong Wang +2

College of Computer Science, Sichuan University · Department of Data and Systems Engineering, The University of Hong Kong

Spatiotemporal Forecasting Video Prediction Convolutional Neural Networks Dynamic Convolution Frequency-Domain Feature Learning Lightweight CNNs

Feb 22, 2026

Efficient Image Super-Resolution with Multi-Scale Spatial Adaptive Attention Networks

This paper introduces a lightweight image super-resolution (SR) network, termed the Multi-scale Spatial Adaptive Attention Network (MSAAN), to address the common dilemma between high reconstruction fidelity and low model complexity in existing SR methods. The core of our approach is a novel Multi-scale Spatial Adaptive Attention Module (MSAA), designed to jointly model fine-grained local details and long-range contextual dependencies. The MSAA comprises two synergistic components: a Global Feature Modulation Module (GFM) that learns coherent texture structures through differential feature extraction, and a Multi-scale Feature Aggregation Module (MFA) that adaptively fuses features from local to global scales using pyramidal processing. To further enhance the network's capability, we propose a Local Enhancement Block (LEB) to strengthen local geometric perception and a Feature Interactive Gated Feed-Forward Module (FIGFF) to improve nonlinear representation while reducing channel redundancy. Extensive experiments on standard benchmarks (Set5, Set14, B100, Urban100, Manga109) across

\times2

,

\times3

, and

\times4

scaling factors demonstrate that both our lightweight (MSAAN-light) and standard (MSAAN) versions achieve superior or competitive performance in terms of PSNR and SSIM, while maintaining significantly lower parameters and computational costs than state-of-the-art methods. Ablation studies validate the contribution of each component, and visual results show that MSAAN reconstructs sharper edges and more realistic textures.

Sushi Rao, Jingwei Li

Zhejiang Gongshang University

Image Super-Resolution Multi-Scale Attention Lightweight CNNs Multi-Scale Feature Fusion

Feb 21, 2026

CLAP Convolutional Lightweight Autoencoder for Plant Disease Classification

Convolutional neural networks have remarkably progressed the performance of distinguishing plant diseases, severity grading, and nutrition deficiency prediction using leaf images. However, these tasks become more challenging in a realistic in-situ field condition. Often, a traditional machine learning model may fail to capture and interpret discriminative characteristics of plant health, growth and diseases due to subtle variations within leaf subcategories. A few deep learning methods have used additional preprocessing stages or network modules to address the problem, whereas several other methods have utilized pre-trained backbone CNNs, most of which are computationally intensive. Therefore, to address the challenge, we propose a lightweight autoencoder using separable convolutional layers in its encoder decoder blocks. A sigmoid gating is applied for refining the prowess of the encoders feature discriminability, which is improved further by the decoder. Finally, the feature maps of the encoder decoder are combined for rich feature representation before classification. The proposed Convolutional Lightweight Autoencoder for Plant disease classification, called CLAP, has been experimented on three public plant datasets consisting of cassava, tomato, maize, groundnut, grapes, etc. for determining plant health conditions. The CLAP has attained improved or competitive accuracies on the Integrated Plant Disease, Groundnut, and CCMT datasets balancing a tradeoff between the performance, and little computational cost requiring 5 million parameters. The training time is 20 milliseconds and inference time is 1 ms per image.

Asish Bera, Subhajit Roy, Sudiptendu Banerjee

Department of Computer Science and Information Systems, Birla Institute of Technology and Science Pilani, Rajasthan, India

Depthwise Separable Convolution Plant Disease Classification Convolutional Autoencoder Convolutional Neural Networks Lightweight CNNs

May 6, 2025

Comparative Analysis of Lightweight CNNs for Resource-Constrained Devices: Predictive Performance, Efficiency Trade-offs, and Initialization Effects

Lightweight convolutional neural networks are often compared using results obtained with different training recipes, input settings, and pretrained checkpoints. Such differences make architecture rankings difficult to interpret. This study presents a controlled benchmark of seven established CNNs across CIFAR-10, CIFAR-100, and Tiny ImageNet under a shared fine tuning protocol. The evaluation reports top-1 accuracy, macro F1, top-5 accuracy, parameter count, FP32 parameter storage, and multiply accumulate operations. EfficientNetV2-S records the highest observed top-1 accuracy on all three datasets, reaching 97.57%, 86.98%, and 78.73%. EfficientNet-B0 remains within 0.85 percentage points of EfficientNetV2-S across the three datasets while requiring only about 21% of its parameters and 14% of its multiply accumulate operations on Tiny ImageNet. It therefore offers a favorable general balance between predictive performance and computational demand. MobileNetV3-Small is a strong candidate for ultra low resource settings. It uses about 40% of the parameters and 15% of the multiply accumulate operations of EfficientNet-B0 while retaining competitive accuracy. A matched comparison of ImageNet pretrained and randomly initialized EfficientNet-B0 and MobileNetV3-Small models shows that the pretrained advantage is substantially larger on CIFAR-100 and Tiny ImageNet than on CIFAR-10 under the fixed protocol. The results provide a focused reference for selecting established lightweight CNNs when predictive quality, parameter storage, and theoretical computation must be considered together.

Tasnim Shahriar

Independent Researcher

Convolutional Neural Networks Lightweight CNNs Image Classification Lightweight Neural Networks

Mar 6, 2023

Evolutionary Deep Nets for Non-Intrusive Load Monitoring

Compact appliance classifiers can support local electricity-load monitoring where memory and computation are constrained. We evaluate adaptive sparse evolutionary training and warm-start compression using synthetic aggregate windows derived from household appliance recordings. A completed convolutional network study trains 120 models over four targets and three seeds with validation-only model selection. Two analyses examine compression with approximately preserved binary accuracy and joint improvement in positive-class F1 and sparsity. Relative to a newly trained fixed sparse evolutionary baseline, the selected compressed policy changes accuracy from 91.53%, while increasing macro F1 to 92.40%. Stored weights decrease by 17.36% and active first-layer connections by 23.93%. Refinement requires additional training. Three seeds and unverified source-window independence prevent claims of statistical equivalence or unseen-house performance.

Jinsong Wang, Kenneth A. Loparo

Non-Intrusive Load Monitoring Sparse Neural Networks Neural Network Compression Lightweight CNNs Dynamic Sparse Training