Currently, with the rapid development of deep learning, deep neural networks (DNNs) have been widely applied in various computer vision tasks. However, in the pursuit of performance, advanced DNN models have become more complex, which has led to a large memory footprint and high computation demands. As a result, the models are difficult to apply in real time. To address these issues, model compression has become a focus of research. Furthermore, model compression techniques play an important role in deploying models on edge devices. This study analyzed various model compression methods to assist researchers in reducing device storage space, speeding up model inference, reducing model complexity and training costs, and improving model deployment. Hence, this paper summarized the state-of-the-art techniques for model compression, including model pruning, parameter quantization, low-rank decomposition, knowledge distillation, and lightweight model design. In addition, this paper discusses research challenges and directions for future work.

Highly developed drone technology enables the use of drones in a wide variety of areas. However, those drones are mainly used in the unmanned aerial vehicles. We believe that underwater drones will become a big research topic and find a market in the near future. We developed an underwater drone with a 360° panoramic camera acting as the “eye”of the drone. The designs are based on the open-source hardware and will be shared as an open-source for contributing to the innovation of manufacturing including drone. The function of the 360° panoramic camera is generated by correcting the images taken by two fisheye lenses. The underwater drone was designed by extending the Raspberry Pi compute module, the frame was designed by OpenSCAD, and the printed circuit board was designed by MakePro. As for the application of the underwater drone, we focused on fish recognition for investigating fish species in a natural lake to help protect the original environment. Fish recognition is based on deep learning, which is the biggest topic in the artificial intelligence research field today. Experimental results show that the function of the underwater drone achieved at diving in the leak automatically. The 360° panoramic images were generated correctly. Fish recognition achieved 87% accuracy by deep learning.

As a promising new paradigm, Vehicular Edge Computing (VEC) can improve the QoS of vehicular applications by computation offloading. However, with more and more computation-intensive vehicular applications, VEC servers face the challenges of limited resources. In this paper, we study how to effectively and economically utilize the idle resources in volunteer vehicles to handle the overloaded tasks in VEC servers. First, we present a model of volunteer assisted vehicular edge computing, in which the cost and utility functions are defined for requesting vehicles and VEC servers, and volunteer vehicles are encouraged to assist the overloaded VEC servers via obtaining rewards from VEC servers. Then, based on Stackelberg game, we analyze the interactions between requesting vehicles and VEC servers, and find the optimal strategies for them. Furthermore, we prove theoretically that the Stackelberg game between requesting vehicles and VEC servers has a unique Stackelberg equilibrium, and propose a fast searching algorithm based on genetic algorithm to find the best pricing strategy for the VEC server. In addition, to maximize the reward of volunteer vehicles, we propose the volunteer task assignment algorithm for optimal mapping between the tasks and volunteer alliances. Finally, the effectiveness of the proposed scheme is demonstrated through a large number of simulations. Compared with other schemes, the proposed scheme can reduce the offloading cost of vehicles and improve the utility of VEC servers.

Industrial visual anomaly detection is critical for ensuring system reliability, safety, and efficiency. This paper presents a comprehensive survey of state-of-the-art anomaly detection techniques, analyzing methodologies, implementations, and recent advancements. Our survey aims to accelerate researchers’ understanding of emerging trends while providing a structured foundation for newcomers. We systematically review 196 recent papers covering five learning strategies, including fully supervised, semi-supervised, self-supervised, weakly supervised, and unsupervised approaches. This paper provides a detailed introduction to twelve industrial anomaly detection methods, revealing their theoretical foundations, technical principles, and practical applications. Additionally, we provide a detailed overview to 2D and 3D datasets for industrial visual anomaly detection. In addition, we critically analyze and summarize the experimental results, identify key performance indicators, and discuss the latest trends in the field of industrial anomaly detection. Beyond analysis, we contribute actionable insights for selecting optimal models for real-world deployment. Finally, we highlight open challenges and outline future research directions to drive innovation in this evolving field. The detailed resources are available at https://github.com/IHPCRits/IAD-Survey.

Oracle bone inscriptions (OBIs) are a kind of hieroglyph, used about 3,600 years ago for divination and the recording of events. The characters on these OBIs are of great interest because they are precursors to the modern Chinese characters widely used across Asia today. However, as the OBIs were only discovered in 1899, there are currently few documents to describe them. Hence, recognizing and unlocking the meaning of OBIs helps to understand the ancient history of China, the evaluation of Chinese characters, and more. Currently, deep learning has made great progress and brought about a revolution in the research field of recognition, and shows good potential to meet the challenges of OBIs recognition. Due to the scarcity of resources, many OBIs contain only a small number of instances, which causes dataset imbalance and limits the accuracy of recognition. This paper attempts to provide a suite of OBIs recognition methods comprising an original OBIs dataset creation, dynamic dataset augmentation, and a novel deep learning-based recognition method. To this end, we create an original OBIs dataset and propose a modified Generative Adversarial Network for augmenting the original OBIs dataset. The augmented data is then dynamically selected for training the deep learning model considering the data imbalance problem. A novel model called C-A Net is proposed for OBIs recognition. The results of evaluation experiments show that the dynamical dataset augmentation can effectively locate a suitable training dataset for the deep learning model and solve the problem of imbalanced OBIs distribution. In addition, the recognition accuracy of C-A Net is 91.10%, which is higher than that of eight state-of-the-art models, and thus effectively suppresses the occurrence of overfitting. We also present an original OBIs dataset named OBI125, which is currently the only rubbing-type OBIs dataset that is open to the public. The code is available at http://www.ihpc.se.ritsumei.ac.jp/obidataset.html.