An improved CSYOLOv8 model based on YOLOv8 model is developed specifically for identifying defects in printed circuit board (PCB). Firstly, a composite backbone network is designed to carry out additional feature extraction, which enriches the expression ability of features and enhances the detection accuracy of the model. Secondly, a YOLO-FPN (Feature pyramid network) structure is designed to supplant the original neck network, which enhances the feature fusion ability of the model and improves the detection accuracy of small target objects. Furthermore, to enhance the model’s capability to extract tubular features, dynamic snake convolution is implemented. Finally, MPDIoU loss function is employed to enhance both the convergence rate and the precision of the model. Experiments show that the mAP of the improved model on the PCB defect dataset reaches 96.6%, which is 4.5% higher than that of the YOLOv8 model, and the number of parameters is only 3256862, and the average detection speed is 51.8 frames per second, which meets the requirements of detection accuracy and efficiency.

An essential component of the intelligent interpretation of remote sensing images is the use of semantic segmentation algorithms to assign feature class labels to individual pixels. Aiming at the problem of low segmentation accuracy of deep neural networks for small-scale objects caused by the large scale difference between different categories of objects in high-resolution remote sensing images, a U-Net++ guided by dual attention semantic segmentation model is proposed in this paper. In the encoding stage of the network, a dual parallel backbone network is constructed to extract features, and mutual attention is utilized to capture the dependencies between pixels of feature maps of different scales, adaptively fusing features of different scales with the same network depth to enhance the attention to small-scale objects. To address the issue of fine segmentation in complex scenes, a spatial and channel hybrid attention mechanism is introduced in the network’s decoding stage to reduce the semantic gap between the outputs of various depth sub-decoders while fusing the semantic information and spatial location representations at various levels therein. The proposed algorithm achieves notable performance metrics, with the mean intersection over union (mIoU) values of 86.77% and 82.73% on the Potsdam dataset and Vaihingen dataset, respectively, accompanied by the mean F₁-score of 92.32% and 90.79%. These results underscore the algorithm’s efficacy in delivering comprehensive segmentation of small scale objects, surpassing the performance of other state-of-the-art semantic segmentation algorithms such as U-Net++, FarSeg, DMAU-Net, and SAPNet.