Lightweight Model Research Articles

EDR-YOLOv8: A lightweight target detection model for UAV aerial photography using advanced feature fusion methods

Abstract Target detection from the aerial perspective of drones plays a crucial role in various fields. However, due to its unique high-altitude overhead view, images captured often exhibit a high proportion of small-sized targets amidst complex backgrounds and varying scales, posing significant challenges for detection. To address these issues, the EDR-YOLOv8 model has been proposed for drone-based aerial target detection. Firstly, the backbone of YOLOv8l is replaced with the high-resolution visual module EfficientViT, reducing the parameter count while maintaining the model's capability to express important features. Secondly, the feature fusion network is redesigned with a four-level prediction layer to enhance the detection accuracy of small-sized targets. Additionally, the lightweight dynamic upsampler DySample is introduced to preserve more detailed target information. Finally, we design the feature fusion module C2f_RepGhost, which integrates the RepGhost bottleneck structure with YOLOv8's C2f, thereby reducing computational complexity. Experimental results demonstrate that EDR YOLOv8 achieves a-4.1% higher mAP@0.5 compared to the baseline YOLOv8l on the VisDrone2019-DET dataset, with a reduction of 40.5% in model size and 42.0% in parameter count. This illustrates that EDR-YOLOv8 achieves both lightweight modeling and improved detection accuracy.

RT-DETRmg: a lightweight real-time detection model for small traffic signs

RT-DETRmg: a lightweight real-time detection model for small traffic signs

TCSRNet: a lightweight tobacco leaf curing stage recognition network model

Due to the constraints of the tobacco leaf curing environment and computational resources, current image classification models struggle to balance recognition accuracy and computational efficiency, making practical deployment challenging. To address this issue, this study proposes the development of a lightweight classification network model for recognizing tobacco leaf curing stages (TCSRNet). Firstly, the model utilizes an Inception structure with parallel convolutional branches to capture features at different receptive fields, thereby better adapting to the appearance variations of tobacco leaves at different curing stages. Secondly, the incorporation of Ghost modules significantly reduces the model’s computational complexity and parameter count through parameter sharing, enabling efficient recognition of tobacco leaf curing stages. Lastly, the design of the Multi-scale Adaptive Attention Module (MAAM) enhances the model’s perception of key visual information in images, emphasizing distinctive features such as leaf texture and color, which further improves the model’s accuracy and robustness. On the constructed tobacco leaf curing stage dataset (with color images sized 224×224 pixels), TCSRNet achieves a classification accuracy of 90.35% with 158.136 MFLOPs and 1.749M parameters. Compared to models such as ResNet34, GhostNet, ShuffleNetV2×1.5, EfficientNet-b0, MobileViT-xs, MobileNetV2, MobileNetV3-large, and MobileNetV3-small, TCSRNet demonstrates superior performance in terms of accuracy, FLOPs, and parameter count. Furthermore, when evaluated on the public V2 Plant Seedlings dataset, TCSRNet maintains an impressive accuracy of 97.15% compared to other advanced network models. This research advances the development of lightweight models for recognizing tobacco leaf curing stages, providing theoretical support for smart tobacco curing technologies and injecting new momentum into the digital transformation of the tobacco industry.

Vehicle identification and analysis based on lightweight yolov5 on edge computing platform

Abstract With the accelerating process of urbanization, the role of intelligent transportation systems in urban traffic management has become more crucial. Nevertheless, traditional surveillance cameras only possess the ability to capture videos and lack the capacity for vehicle detection. Consequently, in order to enhance the intelligent capabilities of front-end surveillance cameras and achieve lightweight model deployment, this research has designed a lightweight detection model that can be deployed on embedded devices. Deploying detection models on embedded devices requires a high level of storage and system computing power, and there exist issues such as model speed, model accuracy, model size, and energy efficiency that are difficult to address in existing studies.Specifically, based on YOLOv5, we first use lightweight structures to replace the C3 module and introduce GSConv and Slim Neck structures to replace the Neck of YOLOv5 in order to reduce the model's parameters and computational complexity. After replacing the model structure, we use global channel pruning to remove redundant information, and use asymmetric quantization to convert model parameters from floating point numbers to fixed point numbers, significantly reducing the model's size and load time, and improving the inference speed. For the target tracking part, we combine the ByteTrack target tracking algorithm with the proposed model, effectively reducing the impact of target occlusion on detection and improving the correlation between video frames. In terms of data recording, detection information such as vehicle color, license plate number, and road blockage level can be uploaded to the database server, and the model's detection results can be encoded using the H.264 video encoding format and uploaded to the streaming media server through streaming media protocols. In the experimental part, we selected the embedded Rk3399pro as the deployment object and achieved 97.8% accuracy in the vehicle counting task, meeting the real-time performance requirements of 31FPS.

LesionScanNet: dual-path convolutional neural network for acute appendicitis diagnosis.

Acute appendicitis is an abrupt inflammation of the appendix, which causes symptoms such as abdominal pain, vomiting, and fever. Computed tomography (CT) is a useful tool in accurate diagnosis of acute appendicitis; however, it causes challenges due to factors such as the anatomical structure of the colon and localization of the appendix in CT images. In this paper, a novel Convolutional Neural Network model, namely, LesionScanNet for the computer-aided detection of acute appendicitis has been proposed. For this purpose, a dataset of 2400 CT scan images was collected by the Department of General Surgery at Kanuni Sultan Süleyman Research and Training Hospital, Istanbul, Turkey. LesionScanNet is a lightweight model with 765K parameters and includes multiple DualKernel blocks, where each block contains a convolution, expansion, separable convolution layers, and skip connections. The DualKernel blocks work with two paths of input image processing, one of which uses 3 × 3 filters, and the other path encompasses 1 × 1 filters. It has been demonstrated that the LesionScanNet model has an accuracy score of 99% on the test set, a value that is greater than the performance of the benchmark deep learning models. In addition, the generalization ability of the LesionScanNet model has been demonstrated on a chest X-ray image dataset for pneumonia and COVID-19 detection. In conclusion, LesionScanNet is a lightweight and robust network achieving superior performance with smaller number of parameters and its usage can be extended to other medical application domains.

A lightweight MHDI-DETR model for detecting grape leaf diseases

Accurate diagnosis of grape leaf diseases is critical in agricultural production, yet existing detection techniques face challenges in achieving model lightweighting while ensuring high accuracy. In this study, a real-time, end-to-end, lightweight grape leaf disease detection model, MHDI-DETR, based on an improved RT-DETR architecture, is presented to address these challenges. The original residual backbone network was improved using the MobileNetv4 network, significantly reducing the model’s computational requirements and complexity. Additionally, a lightSFPN feature fusion structure is presented, combining the Hierarchical Scale Feature Pyramid Network with the Dilated Reparam Block structure design from the UniRepLKNet network. This structure is designed to overcome the challenges of capturing complex high-level and subtle low-level features, and it uses Efficient Local Attention to focus more efficiently on regions of interest, thereby enhancing the model’s ability to detect complex targets while improving accuracy and inference speed. Finally, the integration of GIou and Focaler-IoU into Focaler-GIoU enhances detection accuracy and convergence speed for small targets by focusing more effectively on both simple and difficult samples. The findings from the experiments suggest that The MHDI-DETR model results in a 56% decrease in parameters and a 49% reduction in floating-point operations, respectively, compared with the RT-DETR model, in terms of accuracy, the model achieved precision rates of 96.9%, 92.6%, and 72.5% for accuracy, mAP50, and mAP50:95, respectively. Compared with the RT-DETR model, these represent improvements of 1.9%, 1.2%, and 1.2%. Overall, the MHDI-DETR model surpasses the RT-DETR and other mainstream detection models in both detection accuracy and degree of lightness, achieving dual optimization in efficiency and accuracy, and providing an efficient technical solution for automated agricultural disease management.

Segmentation and Proportion Extraction of Crop, Crop Residues, and Soil Using Digital Images and Deep Learning

Conservation tillage involves covering the soil surface with crop residues after harvest, typically through reduced or no-tillage practices. This approach increases the soil organic matter, improves the soil structure, prevents erosion, reduces water loss, promotes microbial activity, and enhances root development. Therefore, accurate information on crop residue coverage is critical for monitoring the implementation of conservation tillage practices. This study collected “crop–crop residues–soil” images from wheat-soybean rotation fields using mobile phones to create calibration, validation, and independent validation datasets. We developed a deep learning model named crop–crop residue–soil segmentation network (CCRSNet) to enhance the performance of cropland “crop–crop residues–soil” image segmentation and proportion extraction. The model enhances the segmentation accuracy and proportion extraction by extracting and integrating shallow and deep image features and attention modules to capture multi-scale contextual information. Our findings indicated that (1) lightweight models outperformed deeper networks for “crop–crop residues–soil” image segmentation. When CCRSNet employed a deep network backbone (ResNet50), its feature extraction capability was inferior to that of lighter models (VGG16). (2) CCRSNet models that integrated shallow and deep features with attention modules achieved a high segmentation and proportion extraction performance. Using VGG16 as the backbone, CCRSNet achieved an mIoU of 92.73% and a PA of 96.23% in the independent validation dataset, surpassing traditional SVM and RF models. The RMSE for the proportion extraction accuracy ranged from 1.05% to 3.56%. These results demonstrate the potential of CCRSNet for the accurate, rapid, and low-cost detection of crop residue coverage. However, the generalizability and robustness of deep learning models depend on the diversity of calibration datasets. Further experiments across different regions and crops are required to validate this method’s accuracy and applicability for “crop–crop residues–soil” image segmentation and proportion extraction.

A lightweight model for echo trace detection in echograms based on improved YOLOv8

With the rise of underwater unmanned platforms like unmanned boats, ROVs, and AUVs, there’s an increasing need for underwater detection technologies. Researchers have merged scientific echosounders with these platforms for biometric applications. However, current detection models are too parameter-heavy to embed in echosounders and struggle with noisy, irregular, and dense echograms. This paper introduces YOLOv8-SBE, a lightweight fish detection model based on YOLOv8, addressing these issues by enhancing feature extraction, information fusion, and small object recognition. YOLOv8-SBE adds the C2f_ScConv module to improve efficiency and reduce parameters, incorporates the BiFPN structure to enhance information transfer, and uses the EMA attention module for better small target recognition. It reduces computational complexity by 18.5%, decreases model parameters by 40%, and improves mAP0.5 to 79.5% and mAP0.5:0.95 to 58.2%, making it suitable for echosounders with limited resources.

TRMD: a transformer-based reverse design model for quad-band metasurface absorbers

Abstract Metasurfaces have the ability to manipulate electromagnetic waves, which allows for the creation of functions such as perfect absorbers. The goal of a perfect absorber is to achieve high absorption peaks within a specific frequency band. This paper introduces an improved metasurface absorber structure that can achieve efficient absorption in four different frequency bands within the range of 2-9 GHz. In the field of metasurface design, deep learning methods have been recently applied due to their powerful data processing capabilities. However, these methods have primarily used fully connected neural networks and Long Short-Term Memory (LSTM). Despite their capabilities, fully connected networks and LSTM struggle to capture the global information in absorption spectrum data, leading to less accurate predictions. In this study, it was observed that the Transformer model can effectively capture global information using Multi-Head Self-Attention (MHSA) and is not affected by the length of the data. Based on this observation, this paper presents a lightweight model consisting solely of an encoder, achieving a Mean Squared Error (MSE) that is one-twentieth of the State-of-the-Art (SOTA). This model predicts metasurface structure based on target absorption spectra, enabling users to rapidly obtain metasurface absorber structures directly from input absorption spectra. The model consists of two parts: embedding and encoder. The embedding processes input absorption spectra data and adds positional encoding, while the encoder extracts spectral data features. MHSA effectively captures contextual information of absorption spectra, emphasizing key feature information. The final model achieved a MSE convergence of 2 × 10−4 and a coefficient of determination (R 2)value of 0.998, successfully optimizing the design of multi-band metasurface absorbers. Moreover, the predicted results from the model exhibit an absorption spectrum that is highly consistent with the target spectrum.

SR-SqueezeNet: A lightweight hyperspectral identification model for oil spills based on smoothed activation functions

The demand for real-time identification of oil spills in disaster emergency response is urgent, Unmanned Aerial Vehicles (UAVs) are important monitoring means for oil spills by advantage of their flexible, fast and low-cost, so it's crucial of developing lightweight model for UAVs. This paper proposed a lightweight hyperspectral identification model called SR-SqueezeNet, which based on SqueezeNet model and used the designed smooth-type activation function Smooth-ReLU. And this research conducted a series of experiments based on the multi-dimensional airborne images of the oil spills. The results show that SR-SqueezeNet performs the best in both model lightweighting and extraction accuracy. Compared with the traditional SqueezeNet, the identification accuracy is improved by 1.92 %, the number of parameters is reduced by 75.11 %, and the model size is reduced from 26.46 MB to 12.15 MB. Therefore, the SR-SqueezeNet model has potential ability in the practical needs of oil spill UAVs' lightweight detection.

A lightweight road traffic sign detection algorithm based on adaptive sparse channel pruning

Abstract The development of traffic sign recognition (TSR) has become increasingly important for enhancing the safety and convenience of assisted driving. To achieve high accuracy, faster inference speed, and a lightweight model, an improved lightweight TSR network, termed YOLOv8-ALWP, has been proposed. This network incorporates adaptive downsampling to replace the original convolution module in YOLOv8. By employing multiple pooling and convolution operations, it reduces the spatial resolution to extract additional feature information. To accommodate the varying scale characteristics of different traffic signs, large separable kernel attention is introduced to enhance spatial pyramid pooling-fast. Furthermore, the complete intersection over union loss has been improved, and a new Wise-Focaler-EIoU Loss has been proposed to accelerate model convergence and enhance generalization capabilities. Finally, layer-adaptive sparsity for magnitude-based pruning is employed to reduce the model’s parameters, decrease computational complexity, and improve inference speed. Experiments were conducted using the TT100K, Roadsign, CCTSDB, and GTSDB datasets. In the TT100K dataset, compared to the baseline model, the improved algorithm significantly reduced parameters by 64.67%, FLOPs by 44.44%, and increased mAP by 1.7%, precision by 5.5%, and FPS from 70.3 to 81.7, respectively. Under four specific conditions, the improved algorithm effectively addressed the shortcomings of the baseline model, such as missed detections and reduced accuracy. These experimental results indicate that the YOLOv8-ALWP algorithm achieves model lightweighting while enhancing detection accuracy.

Multimodal Fusion-Based Lightweight Model for Enhanced Generalization in Drug-Target Interaction Prediction.

Predicting drug-target interactions (DTIs) with precision is a crucial challenge in the quest for efficient and cost-effective drug discovery. Existing DTI prediction models often require significant computational resources because of the intricate and exceptionally lengthy protein target sequences. This study introduces MMF-DTI, a lightweight model that uses multimodal fusion, to improve the generalizability of DTI predictions without sacrificing computational efficiency. The MMF-DTI model combines four distinct modalities: molecular sequence, molecular properties, target sequence, and target function description. This approach is noteworthy because it is the first to use natural language-based target function descriptions in predicting DTIs. The effectiveness of MMF-DTI has been confirmed through benchmark data sets, demonstrating its comparable performance in terms of generalizability, especially in scenarios with limited information about the drug or target. Remarkably, MMF-DTI accomplishes this using only half of the parameters and 17% of the VRAM compared with previous state-of-the-art models. This allows it to function even in constrained computational environments. The combination of performance and efficiency highlights the potential of multimodal data fusion in improving the overall applicability of models, providing promising opportunities for future drug discovery endeavors.

Innovative Ghost Channel Spatial Attention Network with Adaptive Activation for Efficient Rice Disease Identification

To address the computational complexity and deployment challenges of traditional convolutional neural networks in rice disease identification, this paper proposes an efficient and lightweight model: Ghost Channel Spatial Attention ShuffleNet with Mish-ReLU Adaptive Activation Function (GCA-MiRaNet). Based on ShuffleNet V2, we effectively reduced the model’s parameter count by streamlining convolutional layers, decreasing stacking depth, and optimizing output channels. Additionally, the model incorporates the Ghost Module as a replacement for traditional 1 × 1 convolutions, further reducing computational overhead. Innovatively, we introduce a Channel Spatial Attention Mechanism (CSAM) that significantly enhances feature extraction and generalization aimed at rice disease detection. Through combining the advantages of Mish and ReLU, we designed the Mish-ReLU Adaptive Activation Function (MAAF), enhancing the model’s generalization capacity and convergence speed. Through transfer learning and ElasticNet regularization, the model’s accuracy has notably improved while effectively avoiding overfitting. Sufficient experimental results indicate that GCA-MiRaNet attains a precision of 94.76% on the rice disease dataset, with a 95.38% reduction in model parameters and a compact size of only 0.4 MB. Compared to traditional models such as ResNet50 and EfficientNet V2, GCA-MiRaNet demonstrates significant advantages in overall performance, especially on embedded devices. This model not only enables efficient and accurate real-time disease monitoring but also provides a viable solution for rice field protection drones and Internet of Things management systems, advancing the process of contemporary agricultural smart management.

DeepNeXt: a lightweight polyp segmentation algorithm based on multi-scale attention.

Fast and accurate automatic segmentation of polyps in colonoscopy plays a crucial role in the early diagnosis and treatment of colon cancer. However, the current polyp segmentation algorithms based on deep neural networks suffer from the problems of larger models and lower segmentation accuracy. Meanwhile, achieving accurate segmentation of polyps is to improve the diagnostic efficiency of doctors, and this need motivates us to develop a set of lightweight models so that it can be easily embedded in clinical devices to meet the requirements of practical applications. This study aims to provide effective technical support for the rapid and precise segmentation of polyps in clinical applications. DeepNeXt, an innovative polyp segmentation model grounded in multi-scale attention mechanisms. DeepNeXt incorporates a multi-stage, lightweight convolutional encoder module, leveraging several lightweight convolutional layers for efficient and accurate feature extraction. Furthermore, it features a novel multi-stage feature fusion structure designed to circumvent the potential loss of feature information during the encoding phase. Additionally, the model employs a multi-scale attentional feature encoding module that harnesses multi-branch deep strip convolution techniques to extract multi-dimensional information from the feature maps post-encoding, thereby enhancing the neural network's capability to extract diverse feature information. Experimental validation on the Kvasir Segmentation Dataset (Kvasir-SEG dataset) and Colorectal Cancer-Clinic Datasetbase (CVC-ClinicDB datasets) demonstrates that DeepNeXt outperforms mainstream networks such as U-net, U-net++, TransUnet, SwinUnet, and TGANet in terms of parameters and floating-point operations (FLOPs). DeepNeXt achieved a FLOPs metric of only 3.04 G and a parameters (Params) metric of just 1.51 M, while delivering exceptional performance in segmentation. On the Kvasir-SEG dataset, it reached a mean intersection over union (mIOU) of 83.91, and on the CVC-ClinicDB dataset, 87.37. Additionally, the Dice and Recall metrics also showed superior results, highlighting that DeepNeXt strikes an optimal balance between computational efficiency, model compactness, and segmentation accuracy. In conclusion, we have proposed the DeepNeXt network, a novel lightweight multi-scale attention segmentation network tailored for computationally limited medical devices, which provides strong support for accurate and efficient polyp segmentation in clinical applications.

LightYOLO: Lightweight model based on YOLOv8n for defect detection of ultrasonically welded wire terminations

LightYOLO: Lightweight model based on YOLOv8n for defect detection of ultrasonically welded wire terminations

EpiBrCan-Lite: A Lightweight Deep Learning model for Breast Cancer Subtype Classification using Epigenomic Data

Background and objectivesEarly breast cancer subtypes classification improves the survival rate as it facilitates prognosis of the patient. In literature this problem was prominently solved by various Machine Learning and Deep Learning techniques. However, these studies have three major shortcomings: huge Trainable Weight Parameters (TWP), suffer from low performance and class imbalance problem. MethodsThis paper proposes a lightweight model named EpiBrCan-Lite for classifying breast cancer subtypes using DNA methylation data. This model encompasses three blocks namely Data Encoding, TransGRU, and Classification blocks. In Data Encoding block, the input features are encoded into equal sized chunks and then passed down to TransGRU block which is a modified version of traditional Transformer Encoder (TE). In TransGRU block, MLP module of traditional TE is replaced by GRU module, consisting of two GRU layers to reduce TWP and capture the long-range dependencies of input feature data. Furthermore, output of TransGRU block is passed to Classification block for classifying breast cancer into their subtypes. ResultsThe proposed model is validated using Accuracy, Precision, Recall, F1-score, FPR, and FNR metrics on TCGA breast cancer dataset. This dataset suffers from the class imbalance problem which is mitigated using Synthetic Minority Oversampling Technique (SMOTE). Experimentation results demonstrate that EpiBrCan-Lite model attained 95.85% accuracy, 95.96% recall, 95.85% precision, 95.90% F1-score, 1.03% FPR, and 4.12% FNR despite of utilizing only 1/1500 of TWP than other state-of-the-art models. ConclusionEpiBrCan-Lite model is efficiently classifying breast cancer subtypes, and being lightweight, it is suitable to be deployed on low computational powered devices.

Exploring lightweight machine learning models for personal internet of things (IOT) device security

The proliferation of Internet of Things (IoT) devices in personal and household environments has led to a significant increase in security vulnerabilities. These devices, due to their limited computational resources, often struggle to support conventional security solutions, making them prime targets for cyberattacks. This paper explores the potential of lightweight machine learning (ML) models to enhance the security of personal IoT devices. By leveraging the power of AI, lightweight models can offer real-time threat detection and anomaly identification without compromising the device's performance or requiring extensive computational resources. The paper investigates various ML techniques that are well-suited for IoT environments, such as decision trees, k-nearest neighbours (KNN), and support vector machines (SVM), focusing on their ability to detect intrusions, unauthorized access, and other malicious activities while maintaining efficiency. Additionally, the study highlights the trade-offs between model complexity, accuracy, and resource consumption, offering practical insights for deploying ML solutions in resource-constrained IoT systems. Key challenges, including data privacy, model generalization, and the adaptability of models to diverse IoT ecosystems, are addressed. Finally, the paper discusses future directions for the integration of more advanced lightweight models, such as federated learning and edge computing, which could further enhance security capabilities while ensuring minimal impact on IoT device performance. Through this review, the paper advocates for the adoption of lightweight ML models as a feasible and scalable solution to securing personal IoT devices in an increasingly connected world.

Lightweight spatial-channel feature disentanglement modeling with confidence evaluation for uncertain industrial image

Process uncertainty has a significant impact on industrial image processing. Existing deep learning methods were established on high-quality datasets without considering the uncertainty. This paper proposes lightweight spatial-channel feature disentanglement modeling with confidence evaluation for uncertain industrial images. First, spatial-channel feature disentanglement modeling inspired by tensor decomposition aims to balance the computational efficiency and feature expression capabilities. Second, collaborative learning with confidence evaluation is designed to cope with uncertain samples. Then, representative features are fine-tuned on high-confidence datasets for optimal performance. Complexity analysis and experiments verified the effectiveness, computational efficiency, and robustness of the proposed model.

AKS-YOLOv8: a lightweight and accurate network model for infrared ship detection

Abstract Combining infrared technology and artificial intelligence technology to achieve efficient ship detection is practically important for monitoring and scheduling of ships in harbours. Due to the infrared image texture features are fewer and the background is complex, these lead to the algorithm model having the problems of complex structure, high amount of memory consumption and not being easy to deploy. To address these problems, we propose a lightweight and accurate infrared ship detection model named AKS-YOLOv8, which is based on YOLOv8 design. Firstly, the Split Asymptotic Feature Pyramid Network (SA-FPN) is used in the neck network. It improves model to detect multi-scale infrared ship in large scenes while keeping the model lightweight. Secondly, we introduced the dynamic convolution module KernelWarehouse Dynamic Convolution (KConv) in the backbone network for enhancing the recognition of small targets in infrared images. And we also used FasterBlock instead of Bottleneck to reduce feature map redundancy and improve inference speed. Finally, we adopt Simple, Parameter-free Attention Module (SimAM) to improve the feature extraction ability for key information of infrared ships. To verify the effectiveness of AKS-YOLOv8, a comprehensive test is performed on the infrared ship target recognition database issued by Yantai iraytek Co., Ltd in comparison with some widely-used detection algorithms. The model precision of AKS-YOLOv8 is improved by 1%, and the parameters and model size are reduced by 37.2% and 32.1%, respectively. The results of the experiment indicate that AKS-YOLOv8 has successfully struck a favorable equilibrium between being lightweight and maintaining accuracy. It can provide a valuable technical reference for infrared ship detection technology.

An enhanced YOLOv8‐based bolt detection algorithm for transmission line

AbstractThe current bolt detection for overhead work robots used for transmission lines faces the problems of lightweight algorithms and high accuracy of target detection. To address these challenges, this paper proposes a lightweight bolt detection algorithm based on improved YOLOv8 (you only look once v8) model. Firstly, the C2f module in the feature extraction network is integrated with the self‐calibrated convolution module, and the model is streamlined by reducing spatial and channel redundancies of the network through the SRU and CUR mechanisms in the module. Secondly, the P2 small object detection layer is introduced into the neck structure and the BiFPN network structure is incorporated to enhance the bidirectional connection paths, thereby promoting the upward and downward propagation of features. It improves the accuracy of the network for bolt‐small target detection. The experimental results show that, compared to the original YOLOv8 model, the proposed algorithm demonstrates superior performance on a self‐collected dataset. The mAP accuracy is improved in this paper by 9.9%, while the number of model parameters and the model size is reduced by 0.973 × 106 and 1.7 MB, respectively. The improved algorithm improves the accuracy of the bolt detection while reducing the computation complexity to achieve more lightweight model.