Joint vehicle localization and categorization in high resolution aerial images can provide useful information for applications such as traffic flow structure analysis. To maintain sufficient features to recognize small-scaled vehicles, a regions with convolutional neural network features (R-CNN) -like detection structure is employed. In this setting, cascaded localization error can be averted by equally treating the negatives and differently typed positives as a multi-class classification task, but the problem of class-imbalance remains. To address this issue, a cost-effective network extension scheme is proposed. In it, the correlated convolution and connection costs during extension are reduced by feature map selection and bi-partite main-side network construction, which are realized with the assistance of a novel feature map class-importance measurement and a new class-imbalance sensitive main-side loss function. By using an image classification dataset established from a set of traditional real-colored aerial images with 0.13 m ground sampling distance which are taken from the height of 1000 m by an imaging system composed of non-metric cameras, the effectiveness of the proposed network extension is verified by comparing with its similarly shaped strong counter-parts. Experiments show an equivalent or better performance, while requiring the least parameter and memory overheads are required.

Centralized Training with Decentralized Execution (CTDE) has emerged as a widely adopted paradigm in multi-agent reinforcement learning, emphasizing the utilization of global information for learning an enhanced joint Q-function or centralized critic. In contrast, our investigation delves into harnessing global information to directly enhance individual Q-functions or individual actors. Notably, we discover that applying identical global information universally across all agents proves insufficient for optimal performance. Consequently, we advocate for the customization of global information tailored to each agent, creating agent-personalized global information to bolster overall performance. Furthermore, we introduce a novel paradigm named Personalized Training with Distilled Execution (PTDE), wherein agent-personalized global information is distilled into the agent's local information. This distilled information is then utilized during decentralized execution, resulting in minimal performance degradation. PTDE can be seamless integrated with state-of-the-art algorithms, leading to notable performance enhancements across diverse benchmarks, including the SMAC benchmark, Google Research Football (GRF) benchmark, and Learning to Rank (LTR) task.

Scene classification is one of the fundamental techniques shared by many basic remote sensing tasks with a wide range of applications. As the demands of catering with situations under high variance in the data urgent conditions are rising, a research topic called few-shot scene classification is receiving more interest with a focus on building classification model from few training samples. Currently, methods using the meta-learning principle or graphical models are achieving state-of-art performances. However, there are still significant gaps in between the few-shot methods and the traditionally trained ones, as there are implicit data isolations in standard meta-learning procedure and less-flexibility in the static graph neural network modeling technique, which largely limit the data-to-knowledge transition efficiency. To address these issues, this paper proposed an novel few-shot scene classification algorithm based on a different meta-learning principle called continual meta-learning, which enhances the inter-task correlation by fusing more historical prior knowledge from a sequence of tasks within sections of meta-training or meta-testing periods. Moreover, as to increase the discriminative power between classes, a graph transformer is introduced to produce the structural attention, which can optimize the distribution of sample features in the embedded space and promotes the overall classification capability of the model. The advantages of our proposed algorithm are verified by comparing with nine state-of-art meta-learning based on few-shot scene classification on three popular datasets, where a minimum of a 9% increase in accuracy can be observed. Furthermore, the efficiency of the newly added modular modifications have also be verified by comparing to the continual meta-learning baseline.

This paper studies the tactical decision-making model of short track speed skating based on deep reinforcement learning, so as to improve the competitive performance of corresponding short track speed skaters. Short track speed skating, a traditional discipline in the Winter Olympics since its establishment in 1988, has consistently garnered attention. As artificial intelligence continues to advance, the utilization of deep learning methods to enhance athletes’ tactical decision-making capabilities has become increasingly prevalent. Traditional tactical decision techniques often rely on the experience and knowledge of coaches and video analysis methods that require a lot of time and effort. Consequently, this study proposes a scientific simulation environment for short track speed skating, that accurately simulates the physical attributes of the venue, the physiological fitness of the athletes, and the rules of the competition. The Double Deep Q-Network (DDQN) model is enhanced and utilized, with improvements to the reward function and the distinct description of four tactics. This enables agents to learn optimal tactical decisions in various competitive states with a simulation environment. Experimental results demonstrate that this approach effectively enhances the competition performance and physiological fitness allocation of short track speed skaters.

Centralized Training with Decentralized Execution (CTDE) has emerged as a widely adopted paradigm in multi-agent reinforcement learning, emphasizing the utilization of global information for learning an enhanced joint $Q$-function or centralized critic. In contrast, our investigation delves into harnessing global information to directly enhance individual $Q$-functions or individual actors. Notably, we discover that applying identical global information universally across all agents proves insufficient for optimal performance. Consequently, we advocate for the customization of global information tailored to each agent, creating agent-personalized global information to bolster overall performance. Furthermore, we introduce a novel paradigm named Personalized Training with Distilled Execution (PTDE), wherein agent-personalized global information is distilled into the agent's local information. This distilled information is then utilized during decentralized execution, resulting in minimal performance degradation. PTDE can be seamlessly integrated with state-of-the-art algorithms, leading to notable performance enhancements across diverse benchmarks, including the SMAC benchmark, Google Research Football (GRF) benchmark, and Learning to Rank (LTR) task.