Abstract When capturing distant targets, the video sequence images are affected by atmospheric turbulence, resulting in distortion and blur. In order to restore the degraded images due to atmospheric turbulence in video sequences, this article combines lucky imaging with generative adversarial networks for the first time. The idea of lucky imaging is employed to eliminate geometric distortions, followed by the use of generative adversarial networks to address the blur issue. Additionally, an adaptive restoration method targeting turbulence intensity is proposed to improve the computational efficiency of the proposed approach. Experimental results demonstrate that the combined restoration method of lucky imaging and generative adversarial networks outperforms classical lucky imaging. Specifically, compared to classical lucky imaging, the Brenner gradient function, Laplacian gradient function, Spatial Median Difference (SMD), Entropy, Energy gradient function, PIQE, and Brisque indicators improve by 7.7%, 13.1%, 3.6%, 4.1%, 2.1%, 26.6% and 21.54% (all evaluation indicators in the above improvement rates have undergone logarithmic transformation), respectively. Meanwhile, the proposed adaptive restoration method can improve efficiency by 28%, with greater efficiency gains observed with larger datasets.

Abstract In unmanned aerial vehicle (UAV) aerial target detection tasks, two main challenges exist: the limited computational resources of UAV terminals, which are not conducive to running complex models, and the prevalence of small targets, which can easily lead to missed detections and false positives. To address these issues, this study proposes a lightweight and high‐accuracy small‐object detection algorithm for UAV aerial imagery that is based on YOLOv5s. First, the network structure is optimized by removing the layers in YOLOv5s primarily used for detecting large targets (P4 and P5) and adding layers primarily used for detecting small targets (P2 and P3). This enables the model to focus more on extracting small‐object features. A lightweight dynamic convolution is subsequently introduced in the C3 module, and the lightweight LW_C3 and LW_downsampling modules are designed for feature extraction and downsampling operations. This enhances the model's feature extraction capability while achieving a lightweight design. Finally, the adaptive multi‐scale spatial feature fusion (AMSFF) module is designed to adaptively learn the spatial weights of the feature maps at different levels, thereby further strengthening the effective fusion of multi‐scale features. Experimental results show that the improved YOLO‐Tiny model has higher accuracy and lower complexity, hence validating its excellent performance.

Abstract In order to improve the performance of hyperspectral open set recognition processing with insufficient sample size, the authors propose a new supervised contrastive learning (SCL) framework (FSSCL‐OSC) that can achieve open‐set classification of hyperspectral images in scenarios with very few sample sizes, which consists of three steps. First, supervised contrastive learning (SCL) with geometric transformations is designed, which uses rotated labels as supervision to obtain lower‐level characteristics that more accurately capture various orientations and then makes use of a spectral‐spatial characteristic extraction network to maximize the utilization of HSI's spectrum and spatial information. Next, a class anchor open‐set classification module based on a twin clustering network is designed, which uses SCL and FSL to extract more specific personal information by mining the category‐invariant characteristics present in the known versus unknown class data. Finally, multiple convolution and open‐set recognition (OSC) is performed on the feature blocks. Experimental results on three classical HSI datasets show that FSSCL‐OSC provides a significant improvement over existing methods, under a sample size of only 10%, the overall accuracy reached 82.38%, 90.76% and 84.70%, respectively.

Abstract In deep neural networks, performance can degrade when test data distributions differ from training data. Unsupervised Domain Generalization (UDG) aims to improve generalization across unseen domains by leveraging multiple source domains without supervision. Traditional methods focus on extracting domain‐invariant features, potentially at the expense of feature space integrity and generalization potential. We presents a Multi‐Domain Representation Network (MDRN) for unsupervised multi‐domain learning. MDRN innovates by disentangling and preserving both domain‐invariant and domain‐specific features through an unsupervised cross‐domain reconstruction task. It employs content encoders for domain‐invariant features and multi‐domain style encoders for domain‐specific characteristics. By merging these features based on domain similarity, MDRN constructs a comprehensive feature space that enhances image reconstruction across domains. Additionally, MDRN integrates domain‐specific classifiers, which learn domain classification and provide weighted fusion of domain‐specific features. This design facilitates effective inter‐domain distance measurement and feature integration. Experiments on PACS and DomainNet show MDRN's superior performance over existing state‐of‐the‐art UDG approaches, highlighting its effectiveness in handling distribution shifts between source and target domains.

Abstract Gallbladder cancer is a fatal disease, and its early diagnosis can significantly impact patient treatment. Ultrasound imaging is often the initial diagnostic test for gallbladder cancer, making the enhancement of cancer detection accuracy from these images crucial. Despite the promising results of artificial intelligence techniques in disease diagnosis, their black‐box nature hinders the reliability of their results and their practical application. Therefore, it is essential not to rely solely on a single model's output and to further investigate for more reliable outcomes. This study presents a step‐by‐step structural investigation of forming an end‐to‐end model, a conjunction of two convolutional neural network based methods, for detecting gallbladder conditions. The final model, leveraging feature fusions and hierarchical classification, achieved a high accuracy of 92.62% for detecting normal, benign, and malignant gallbladders. It also achieved a remarkable accuracy of 98.36% for classifying normal and non‐normal instances and 92.22% for classifying benign and malignant cases. Finally, comprehensive post‐processing investigations, including cross‐validation, temperature scaling, and uncertainty estimation, along with error analysis, are conducted to gain more insights into the model's output. Among these insights, the model demonstrated resilience of its results to active dropout and augmentation at the inference phase. Furthermore, when applied with test‐time data augmentation, uncertainty estimation methods have better distinguishability between the uncertainties of correctly and incorrectly classified instances, which provides additional information about the model's output. The source code of experiments conducted in this study is available at https://github.com/SaraDadjouy/GBCRet .

Abstract An intelligent retrievable object‐tracking system assists users in quickly and accurately locating lost objects. However, challenges such as real‐time processing on edge devices, low image resolution, and small‐object detection significantly impact the accuracy and efficiency of video‐stream‐based systems, especially in indoor home environments. To overcome these limitations, a novel real‐time intelligent retrievable object‐tracking system is designed. The system incorporates a retrievable object‐tracking algorithm that combines DeepSORT and sliding window techniques to enhance tracking capabilities. Additionally, the YOLOv7‐small‐scale model is proposed for small‐object detection, integrating a specialized detection layer and the convolutional batch normalization LeakyReLU spatial‐depth convolution module to enhance feature capture for small objects. TensorRT and INT8 quantization are used for inference acceleration on edge devices, doubling the frames per second. Experiments on a Jetson Nano (4 GB) using YOLOv7‐small‐scale show an 8.9% improvement in recognition accuracy over YOLOv7‐tiny in video stream processing. This advancement significantly boosts the system's performance in efficiently and accurately locating lost objects in indoor home settings.

Abstract As UAVs are more and more widely used in military and civilian fields, their intelligent applications have also been developed rapidly. However, high‐precision autonomous landing is still an industry challenge. GPS‐based methods will not work in places where GPS signals are not available; multi‐sensor combination navigation is difficult to be widely used because of the high equipment requirements; traditional vision‐based methods are sensitive to scale transformation, background complexity and occlusion, which affect the detection performance. In this paper, we address these problems and apply deep learning methods to target detection in the UAV landing phase. Firstly, we optimize the backbone network of YOLOX and propose the Swin Transformer based YOLOX (Swin‐YOLOX) UAV landing visual positioning algorithm. Secondly, based on the UAV‐VPD database, a batch of actual acquisition data is added to build the UAV‐VPDV2 database by AI annotation method. And finally, the RBN data batch normalization method is used to improve the performance of the model in extracting effective features from the data. Extensive experiments have shown that the AP50 of the proposed method can reach 98.7%, which is superior to other detection models, with a detection speed of 38.4 frames/second, and can meet the requirements of real‐time detection.

Abstract Unsupervised person re‐identification has attracted vital interest because of its ability to protect privacy, significantly lower the expense of manual annotation, and eliminate the need for data labels. General unsupervised methods train the network only through global features, which causes the fine‐grained information contained in local features to be ignored in the recognition process, resulting in large amounts of label noise and affecting the recognition accuracy. Moreover, more robust pedestrian features can also improve the accuracy of clustering and enable unsupervised person re‐identification to obtain better results. To address these issues, first, a dual‐branch structure was proposed, which separately obtains the global features of the pedestrian and the local features by dividing the global features into a few equal sections. Then, an adaptive information supplementation (AIS) method based on the k‐nearest neighbor algorithm is designed to ascertain each local feature's relevance to the global features, calculating adaptive weight scores for information supplementation. Finally, these weight scores are used to reallocate the weights of the global features in each part, acquiring features that contain more pedestrian information during the representation learning process. These better features are used to reduce label noise to obtain more accurate pseudo‐labels. Second, an adaptive foreground enhancement module (AFEM) was proposed and inserted before clustering to increase the robustness of pedestrian features, which increases the precision of the pseudo‐labels that are produced after clustering. Experiments on Market‐1501, DukeMTMC‐reID, and MSMT17 demonstrate that the proposed method achieves better results than state‐of‐the‐art methods in fully unsupervised person re‐identification tasks.

Abstract Traffic sign detection is essential to an intelligent driving assistance system. The deep learning‐based algorithm proposed in this paper aims to address the issue of low detection accuracy caused by the small size and high density of traffic signs in real‐world traffic scenarios. First, to improve the feature extraction module of the backbone network and to increase the model's ability to capture contextual information, partial convolution (PConv) is introduced. Second, to prevent information loss during the downsampling process, a cross‐stage atrous spatial pyramid (ASPPFCSPC) is constructed using atrous convolution. This method combines feature map information from various scales and expands the receptive field. Lastly, the small‐target detection precision is improved by incorporating an additional small‐target detection head, which uses high‐resolution feature maps for shallow features. The detection head is decoupled to extract the location and class information of the predicted target separately, thereby enhancing the generalization ability of the proposed model. Experiments have demonstrated the superiority of the proposed algorithm, as testing on the TT100K dataset resulted in a mAP@0.5 of 91.2% and a mAP@0.5:0.95 of 71.8% using the proposed algorithm.

Abstract Conventional computed tomography (CT) images often suffer from blurred edges and unclear details. Image super‐resolution methods can significantly enhance CT image quality, thereby improving diagnostic accuracy. To better extract detailed features and enhance the cascading effects of different feature levels, we propose a novel medical image super‐resolution algorithm that integrates discrete wavelet transform and multi‐scale adaptive feature selection. Our approach uses both the low‐resolution image and its high‐frequency component from the frequency domain as network inputs, with the high‐frequency component providing learning supervision, which enhances detail fidelity in reconstruction. Additionally, we introduce a multi‐scale adaptive feature selection module to learn from different layers of CT images and their inter‐layer correlations. Finally, the pixel information is efficiently integrated by a coordinate attention mechanism incorporating the concept of squeeze excitation. Experimental results show that our method outperforms state‐of‐the‐art methods, achieving superior reconstruction at scale factors of 2, 4, and 8, especially at scale factor 8, where it surpasses others by 1.12 in PSNR, 0.0145 in SSIM, and 0.0038 in LPIPS. Visually, our method also delivers more accurate details and better perceptual quality.