Deep learning models often suffer from performance degradation in unseen domains, posing a risk for safety-critical applications such as autonomous driving. To tackle this problem, recent studies have leveraged pre-trained Visual Foundation Models (VFMs) to enhance generalization. However, exsiting works mainly focus on designing intricate networks for VFMs, neglecting their inherent strong generalization potential. Moreover, these methods typically perform inference on low-resolution images. The loss of detail hinders accurate predictions in unseen domains, especially for small objects. In this paper, we argue that simply fine-tuning VFMs and leveraging high-resolution images unleash the power of VFMs for generalizable semantic segmentation. Therefore, we design a VFM-based segmentation network (VFMNet) that adapts VFMs to this task with minimal fine-tuning, preserving their generalizable knowledge. Then, to fully utilize high-resolution images, we train a Mask-guided Refinement Network (MGRNet) to refine VFMNet's predictions combining detailed image features. Furthermore, we adopt a two-stage coarse-to-fine inference approach. MGRNet is used to refine the low-confidence regions predicted by VFMNet to obtain fine-grained results. Extensive experiments demonstrate the effectiveness of our method, outperforming state-of-the-art methods by 3.3% on the average mIoU in synthetic-to-real domain generalization.

Collecting and annotating data for semantic segmentation can end up costing a lot of time and energy. Unsupervised Domain Adaptation (UDA) for semantic segmentation allows models trained on certain source domain data (such as the GTA synthetic dataset) to be applied to certain target data (like the Cityscapes real dataset), significantly decreasing the requirement for target-domain manual pixel-level annotations.In this paper, we suggest a cross-domain unified semantic segmentation network training framework, the Attention Distribution Adaptation Network (ADAN). It (1) proposes the Content Consistency Transformation (CCT), which maps source domain data to an intermediate domain that has a data distribution that is comparable to that of the target domain, and (2) introduces the Attention Adaptation Module (AAM), which bolsters the synchronization of attention between the intermediate domain and the target domain. ADAN achieved unprecedented mIoUs of 77.2 and 68.8 on GTA→Cityscapes and Synthia→Cityscapes, respectively, corresponding to improvements of +1.3 and +0.6 over the state of the art.

Motion planning is a difficult task, especially when generating feasible future trajectories in complex and interactive scenarios. While recent advancements in imitation-based planning have shown significant progress, this approach often encounters causal confusion in dynamic traffic environments. This confusion will cause the planner to incorrectly associate certain actions with outcomes, leading to suboptimal or unsafe plans. To address this, we introduce a novel framework called$\overline{C}^{2}L$, which improves the planner's latent Causal understanding by incorporating Contrastive Learning and counterfactual data augmentation. Additionally, we propose a shortcut eliminator to extract copycat-free features from history states, reducing the impact of temporal spurious correlations. We validate our method on the nuPlan and interPlan benchmarks, with extensive experiments demonstrating that$C^{2}L$delivers highly competitive performance compared to state-of-the-art methods.

As a promising implementation model of payment channel network (PCN), payment channel hub (PCH) could achieve high throughput by providing stable off-chain transactions through powerful hubs. However, existing PCH schemes assume hubs are preplaced in advance, not considering payment requests' distribution and may affect network scalability, especially network load balancing. In addition, current source routing protocols with PCH allow each sender to make routing decision on his/her own request, which may have a bad effect on performance scalability (e.g., deadlock) for not considering other senders' requests. This paper proposes a novel multi-PCHs solution with high scalability. First, we are the first to study the PCH placement problem and propose optimal/approximation solutions with load balancing for small-scale and large-scale scenarios, by trading off communication costs among participants and turning the original NP-hard problem into a mixed-integer linear programming (MILP) problem solving by supermodular techniques. Then, on global network states and local directly connected clients' requests, a routing protocol is designed for each PCH with a dynamic adjustment strategy on request processing rates, enabling high-performance deadlock-free routing. Extensive experiments show that our work can effectively balance the network load, and improve the performance on throughput by 29.3% on average compared with state-of-the-arts.

An automated driving system (ADS), as the brain of an autonomous vehicle (AV), should be tested thoroughly ahead of deployment. ADS must satisfy a complex set of rules to ensure road safety, e.g., the existing traffic laws and possibly future laws that are dedicated to AVs. To comprehensively test an ADS, we would like to systematically discover diverse scenarios in which certain traffic law is violated. The challenge is that (1) there are many traffic laws (e.g., 13 testable articles in Chinese traffic laws and 16 testable articles in Singapore traffic laws, with 81 and 43 violation situations respectively); and (2) many of traffic laws are only relevant in complicated specific scenarios.

Federated Learning (FL) enables the deployment of distributed machine learning models over the cloud and Edge Devices (EDs) while preserving the privacy of sensitive local data, such as electronic health records. However, despite FL advantages regarding security and flexibility, current constructions still suffer from some limitations. Namely, heavy computation overhead on limited resources EDs, communication overhead in uploading converged local models' parameters to a centralized server for parameters aggregation, and lack of guaranteeing the acquired knowledge preservation in the face of incremental learning over new local data sets. This paper introduces a secure and resource-friendly protocol for parameters aggregation in federated incremental learning and its applications. In this study, the central server relies on a new method for parameters aggregation called orthogonal gradient aggregation. Such a method assumes constant changes of each local data set and allows updating parameters in the orthogonal direction of previous parameters spaces. As a result, our new construction is robust against catastrophic forgetting, maintains the federated neural network accuracy, and is efficient in computation and communication overhead. Moreover, extensive experiments analysis over several significant data sets for incremental learning demonstrates our new protocol's efficiency, efficacy, and flexibility.

Indoor positioning systems are becoming increasing popular recently. While most existing indoor positioning studies focus on improving accuracy, less attention is paid to the latency problem. The traditional fusion algorithm uses the received signal strength-based (RSS-Based) positioning result to correct the current position of the system. However, it fails to keep up with the actual moving speed of the user during the navigation. The location retrospective adjustment (LRA) method proposed in this paper uses the RSS-Based positioning result to correct the past position of the system, which can effectively eliminate positioning delay and improve the real-time response of navigation. We tested in a 70 m linear promenade and found that the addition of LRA results in a reduction of the positioning error around −0.3 to +0.4 m, which improves 85%. Additionally, the LRA method alleviates the requirements for the immediate response of RSS positioning, and the RSS positioning algorithm can be moved to the cloud. It reduces the download resources and computing load on the mobile phone. The complete indoor navigation application is presented in HTML5 which allows users to navigate without having to download the APP in advance, and it takes only 4–9 s for users to launch the application for the first time. We tested the application in a hospital with a total floor area of 79,000 m2 in 7 buildings. The system achieves an average positioning accuracy of 0.65 m at a long navigation distance of 220 m. To our knowledge, this paper is the first to consider the latency issue in indoor navigation. The proposed LRA approach improves real-time navigation performance, lightens the computation load on the mobile phone, and allows cloud-based positioning systems to provide stable and accurate navigation even under poor network quality in crowded areas.