CAE-YOLOv11n: Research on Commodity Classification for Retail Automated Checkout Systems

Aiming at the problems of leakage, misdetection and low detection efficiency of transmission line foreign object detection in railroad environment, we propose an improved railroad transmission line foreign object detection algorithm MRS-YOLO based on YOLOv11n. Firstly, a multi-scale Adaptive Kernel Depth Feature Fusion (MAKDF) module is proposed and fused with the C3k2 module to form C3k2_MAKDF, which enhances the model's feature extraction capability for foreign objects of different sizes and shapes. Secondly, a novel Re-calibration Feature Fusion Pyramid Network(RCFPN) is designed as a Neck structure to improve the feature fusion capability of the model. Then, Spatial and Channel Reconstruction Detect Head (SC_Detect) based on spatial and channel preprocessing is designed to improve the overall detection accuracy of the model. Finally, the channel pruning technique is used to reduce the redundancy of the improved model, drastically reduce Parameters and GFLOPs, and improve the detection efficiency. The experimental results show that the mAP50 and mAP50:95 of the MRS-YOLO algorithm proposed in this paper are improved to 94.8% and 86.4%, respectively, which are 0.7 and 2.3 percentage points higher compared to the baseline, while Parameters and GFLOPs are reduced by 44.2% and 17.5%, respectively. It is demonstrated that the improved algorithm can be better applied to the task of foreign object detection in railroad transmission lines.

With special consideration for complex scenes and densely distributed small objects, this frequently leads to serious false and missed detections for unmanned aerial vehicle (UAV) images in small object detection scenarios. Consequently, we propose a UAV image small object detection algorithm, termed SMA-YOLO. Firstly, a parameter-free simple slicing convolution (SSC) module is integrated in the backbone network to slice the feature maps and enhance the features so as to effectively retain the features of small objects. Subsequently, to enhance the information exchange between upper and lower layers, we design a special multi-cross-scale feature pyramid network (M-FPN). The C2f-Hierarchical-Phantom Convolution (C2f-HPC) module in the network effectively reduces information loss by fine-grained multi-scale feature fusion. Ultimately, adaptive spatial feature fusion detection Head (ASFFDHead) introduces an additional P2 detection head to enhance the resolution of feature maps to better locate small objects. Moreover, the ASFF mechanism is employed to optimize the detection process by filtering out information conflicts during multi-scale feature fusion, thereby significantly optimizing small object detection capability. Using YOLOv8n as the baseline, SMA-YOLO is evaluated on the VisDrone2019 dataset, achieving a 7.4% improvement in mAP@0.5 and a 13.3% reduction in model parameters, and we also verified its generalization ability on VAUDT and RSOD datasets, which demonstrates the effectiveness of our approach.

Adaptive spectral-spatial feature fusion network for hyperspectral image classification using limited training samples

In general object detection, scale variation is always a big challenge. At present, feature pyramid networks are employed in numerous methods to alleviate the problems caused by large scale range of objects in object detection, which makes use of multi-level features extracted from the backbone for top-down upsampling and fusion to acquire a set of multi-scale depth image features. However, the feature pyramid network proposed by Ghiasi et al. adopts a simple fusion method, which fails to consider the fusion feature context, and therefore, it is difficult to acquire good features. In addition, the fusion of multi-scale features directly by traditional upsampling is prone to feature misalignment and loss of details. In this paper, an adaptive feature pyramid network is proposed based on the feature pyramid network to alleviate the foregoing potential problems, which includes two major designs, i.e., adaptive feature upsampling and adaptive feature fusion. The adaptive feature upsampling aims to predict a group of sampling points of each pixel through some models, and constitute feature representation of the pixel by feature combination of sampling points, while adaptive feature fusion is to construct pixel-level fusion weights between fusion features through attention mechanism. The experimental results verified the effectiveness of the method proposed in this paper. On the public object detection dataset MS-COCO test-dev, Faster R-CNN model achieved performance improvement of 1.2 AP by virtue of the adaptive feature pyramid network, and FCOS model could achieve performance improvement of 1.0 AP. What's more, the experiments also validated that the adaptive feature pyramid network proposed herein was more accurate for object localization.

A multi-scale semantic feature fusion method for remote sensing crop classification

Online knowledge distillation conducts knowledge transfer among all student models to alleviate the reliance on pre-trained models. However, existing online methods rely heavily on the prediction distributions and neglect the further exploration of the representational knowledge. In this paper, we propose a novel Multi-scale Feature Extraction and Fusion method (MFEF) for online knowledge distillation, which comprises three key components: Multi-scale Feature Extraction, Dual-attention and Feature Fusion, towards generating more informative feature maps for distillation. The multiscale feature extraction exploiting divide-and-concatenate in channel dimension is proposed to improve the multi-scale representation ability of feature maps. To obtain more accurate information, we design a dual-attention to strengthen the important channel and spatial regions adaptively. Moreover, we aggregate and fuse the former processed feature maps via feature fusion to assist the training of student models. Extensive experiments on CIF AR-10, CIF AR-100, and CINIC-10 show that MFEF transfers more beneficial representational knowledge for distillation and outperforms alternative methods among various network architectures

Image dehazing is critical for visual enhancement and a wide range of computer vision applications. Despite significant advancements, challenges remain in preserving fine details and adapting to diverse, non-uniformly degraded scenes. To address these issues, we propose a novel image dehazing method that introduces a contrastive learning framework, enhanced by the InfoNCE loss, to improve model robustness. In this framework, hazy images are treated as negative samples and their clear counterparts as positive samples. By optimizing the InfoNCE loss, the model is trained to maximize the similarity between positive pairs and minimize that between negative pairs, thereby improving its ability to distinguish haze artifacts from intrinsic scene features and better preserving the structural integrity of images. In addition to contrastive learning, our method integrates a multi-scale dynamic feature fusion with a hybrid attention mechanism. Specifically, we introduce dynamically adjustable frequency band filters and refine the hybrid attention module to more effectively capture fine-grained, cross-scale image details. Extensive experiments on the RESIDE-6K and RS-Haze datasets demonstrate that our approach outperforms most existing methods, offering a promising solution for practical image dehazing applications.

Most existing target detection models are designed for image targets in natural scenarios and the detection results of small targets in aerial images are less than satisfactory. This paper tries to solve the locating and classification problem of small targets in aerial images from the perspectives of fusion between shallow features and deep features, receptive field enhancement, and a lightweight feature extraction network. To realize accurate detection of small targets in aerial images, on the basis of SSD (Single Shot MultiBox Detector), an aerial image target detection model MF-SSD based on multi-scale feature fusion and receptive field enhancement is proposed. In this model, a feature fusion sub-network is established, in which, the two-level fusion of shallow features and skip-connection fusion of intermediate features are provided. In addition, a multi-branch Inception structure D-Inception based on dilated convolution is utilized to achieve receptive field enhancement, which enables the system to better extract target features and adapt to the scale change of target. To address the increased computational complexity of the model after feature fusion and receptive field enhancement processing, a lightweight convolutional neural network based on Mobilenet is used to replace the basic network, which can not only reduce the complexity of the network model but also maintain high detection precision. The experimental results show that the target detection model MF-SSD can be used to effectively detect small targets in aerial images.KeywordsSmall target detectionFeature fusionReceptive field enhancementLightweight convolutional neural network (CNN)

Brain tumor detection in MRI images remains a significant challenge with complex structures, intra-class variation, and thin boundary areas often leading to misclassification. Alleviating this challenge, this work introduces an Adaptive Multi-Scale Feature Fusion framework that combines Capsule Networks with Deep Belief Networks in order to boost the reliability of diagnosis. The solution is tailored to capture spatial hierarchies, variation in poses, and orientation information effectively while adapting features at various scales in order to provide more holistic representation. The goal is to improve classification precision, reduce false positives, and provide consistent outputs in the presence of various types of tumors. The novelty of the strategy is the preservation of structural information based on capsule-based encoding while utilizing high-level abstraction from the result of deep probabilistic modeling such that the system is rendered better compared to conventional CNN-based systems. The system as proposed includes the stages of preprocessing, segmentation, feature fusion, and classification, thus offering a promising tool in the automated clinical support system in neuroimaging. This research aligns with the Sustainable Development Goal (SDG 3): Good Health and Well-Being, by contributing to improved healthcare diagnostics and early tumor detection.

To address the problem of inaccurate representation, inadequate fusion and unsmooth results in video-based single person three-dimensional human pose estimation, a multi-scale spatial-temporal feature fusion method is proposed. Firstly, the joint, limb and upper/lower body tokens were defined in spatial domain to represent the spatial multi-scale features of human body using positional embeddings. Secondly, the spatial multi-scale feature fusion module was constructed based on self-attention mechanism and multilayer perceptron to fuse joint, limb and upper/lower body features, obtaining initial pose feature sequence. Lastly, the temporal multi-scale encoding was established for temporal feature fusion to acquire final pose feature sequence, and optimize the generation of refined three-dimensional human pose through temporal decoding. Experimental results on Human3.6M dataset show that the mean per joint position error and joint velocity errors are 33.6 and 2.4 respectively, which reduce by 2.3% and 4.0%. The proposed method can improve three-dimensional human pose estimation accuracy and generate precise and smooth results while reducing computational cost. Furthermore, experimental results on HumanEva-I dataset show that the proposed method also has a certain degree of generalization ability.

The classification of high-resolution (HR) synthetic aperture radar (SAR) images is of great importance for SAR scene interpretation and application. However, the presence of intricate spatial structural patterns and complex statistical nature makes SAR image classification a challenging task, especially in the case of limited labeled SAR data. This paper proposes a novel HR SAR image classification method, using a multi-scale deep feature fusion network and covariance pooling manifold network (MFFN-CPMN). MFFN-CPMN combines the advantages of local spatial features and global statistical properties and considers the multi-feature information fusion of SAR images in representation learning. First, we propose a Gabor-filtering-based multi-scale feature fusion network (MFFN) to capture the spatial pattern and get the discriminative features of SAR images. The MFFN belongs to a deep convolutional neural network (CNN). To make full use of a large amount of unlabeled data, the weights of each layer of MFFN are optimized by unsupervised denoising dual-sparse encoder. Moreover, the feature fusion strategy in MFFN can effectively exploit the complementary information between different levels and different scales. Second, we utilize a covariance pooling manifold network to extract further the global second-order statistics of SAR images over the fusional feature maps. Finally, the obtained covariance descriptor is more distinct for various land covers. Experimental results on four HR SAR images demonstrate the effectiveness of the proposed method and achieve promising results over other related algorithms.

The performance of underwater target detection algorithms is affected by poor imaging quality in underwater environments. Due to the arithmetic power limitation of underwater devices, existing deep learning networks are unable to provide efficient detection processes with high detection accuracy. Lightweight CNN models have been actively applied for underwater environment detection, yet their lite feature fusion networks cannot provide effective fusion effects and reduce the detection accuracy. In this paper, a lightweight algorithm based on multi-scale feature fusion was proposed, with the model parameters greatly reduced, improving the target detection accuracy. The forward propagation memory overhead is reduced by using multi-scale shared convolutional kernels and pooling operations to co-construct the query matrix in the Tansformer encoding stage. Then, the feature fusion path is optimized in order to enhance the connection of multi-scale features. A multiscale feature adaptive fusion strategy is used to enhance the detection performance and reduce the dependence on the complex feature extraction network. The feature extraction network is also reparameterized to simplify the operation. Using the UPRC offshore dataset for validation, the study results have demonstrated that the statistical mAP metrics validate the detection accuracy. Compared with SSD, RetinaNet and YOLOv5-s improved by 13%, 8.6%, and 0.8%, while the number of parameters decreased by 76.09%, 89.74%, and 87.67%. In addition, compared with the YOLOv5-lite model algorithm with the same parameter volume, the mAP is improved by 3.8%, which verifies the accuracy and efficiency of the algorithm in this paper.

Object detection in remote sensing images faces the challenges of a complex background, large object size variations, and high inter-class similarity. To address these problems, we propose an adaptive adjacent layer feature fusion (AALFF) method, which is developed on the basis of RTMDet. Specifically, the AALFF method incorporates an adjacent layer feature fusion enhancement (ALFFE) module, designed to capture high-level semantic information and accurately locate object spatial positions. ALFFE also effectively preserves small objects by fusing adjacent layer features and employs involution to aggregate contextual information in a wide spatial range for object essential features extraction in complex backgrounds. Additionally, the adaptive spatial feature fusion (ASFF) module is introduced to guide the network to select and fuse the crucial features to improve the adaptability to objects with different sizes. The proposed method achieves mean average precision (mAP) values of 77.1%, 88.9%, and 95.7% on the DIOR, HRRSD, and NWPU VHR-10 datasets, respectively. Notably, our approach achieves mAP75 values of 60.8% and 79.0% on the DIOR and HRRSD datasets, respectively, surpassing the state-of-the-art performance on the DIOR dataset.

Object detection (OD) in unmanned aerial vehicle (UAV) images faces many challenges, with diverse-scale objects and small objects being particularly prominent issues. To alleviate these challenges, we propose a novel multiscale feature learning and feature fusion network under the guidance of deformable convolution. First, a deformable convolution-guided feature learning (DCGFL) block is designed in the backbone to extract more effective multiscale features. The DCGFL block leverages the adaptability of deformable convolution to the shapes and scales of objects, akin to spatial attention. Moreover, it also employs channel attention to identify important feature maps. Hence, the proposed backbone possesses the functionality of spatial attention and channel attention. Second, in the neck, we devise a simple generalized feature pyramid network (SimpleGFPN) with several deformable convolution-guided feature fusion (DCGFF) blocks to fuse multiscale features. The proposed neck has cross-layer and cross-scale pathways, facilitating effective information exchange and fusion between shallow spatial and deep semantic features. Third, the SIoU loss is used to better model the bounding box regression loss. Finally, experimental results on the VisDrone2021 and UAVDT datasets show that the proposed method outperforms the compared OD methods. In terms of mean average precision, we obtain 37.8% on VisDrone2021 and 18.5% on UAVDT.

Objective To address the inefficiency and high cost of manual road inspections and the limited accuracy of existing computer vision methods, this study proposes a multi-scale road defect detection model, LTF-YOLO, based on YOLO11s. The model aims to enhance both the accuracy and robustness of automated road defect detection. Methods In the feature-extraction stage, an LMSFA module replaces the original C3k2 module in YOLO11s. This module employs a hierarchical large-kernel convolution combined with group convolution and block-concatenation strategies to achieve efficient multi-scale feature aggregation. During feature fusion, an improved SPPFMPF module introduces average pooling and channel attention branches, with learnable weights enabling adaptive fusion of multi-source features. In the detection head, the TADDH module separates classification and regression subspaces through a task-decoupling mechanism. The regression branch incorporates DyDCNv2 dynamic convolution for spatial adaptive alignment, while a confidence-guided mechanism enhances detection reliability. Results Experiments on the SVRDD dataset demonstrate that, compared with the baseline YOLO11s, LTF-YOLO improves Precision by 4.4%, rising from 70.2 to 74.6, mAP@50 by 3.3%, improving from 66.4 to 69.7, and mAP@50–95 by 3.8%, rising from 39.4 to 43.2. Cross-dataset experiments on the RDD2022 dataset further demonstrate the strong generalization ability of LTF-YOLO, with mAP@50 increasing from 47.2 to 49.2 while maintaining a lightweight architecture. The proposed model achieves more accurate identification of cracks and potholes under complex road conditions, effectively reducing missed and false detections. Conclusion Through innovations in multi-scale feature extraction, adaptive feature fusion, and task-decoupled detection head design, LTF-YOLO significantly enhances detection accuracy and robustness. The model maintains high precision while remaining lightweight, providing an efficient and scalable solution for intelligent road maintenance and traffic safety monitoring.