Unsupervised domain adaptation aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Existing methods, whether based on distribution matching or self-supervised learning, often focus solely on classifying individual source samples, potentially overlooking discriminative information. To address this limitation, we propose FlowUDA, a novel plugin method that enhances existing UDA frameworks by constructing semantically invariant flows from individual source samples to corresponding target samples, forming cross-domain trajectories. By leveraging a diffusion network guided by ordinary differential equations, FlowUDA ensures these flows preserve the topological structure of the source domain, maintaining their distinguishability. Our method then classifies these flows by sampling points along them and transferring labels from source samples, effectively capturing spatial relationships between domains. In essence, FlowUDA transforms the traditional point-based classification on individual source samples into flow-based classification on flows, allowing the model to learn richer, more discriminative features that bridge the gap between source and target domains. Extensive experiments on standard benchmarks demonstrate that integrating FlowUDA into existing UDA methods leads to notable performance gains, highlighting its effectiveness in addressing domain shift challenges.

Unmanned Aerial Vehicle Object Detection (UAVOD) presents unique challenges due to varying altitudes, dynamic backgrounds, and the small size of objects. Traditional detection methods often struggle with these challenges, as they typically rely on visual feature only and fail to extract the semantic relations between the objects. To address these limitations, we propose a novel approach named Self-Prompting Analogical Reasoning (SPAR). Our method utilizes the vision-language model (CLIP) to generate context-aware prompts based on image feature, providing rich semantic information that guides analogical reasoning. SPAR includes two main modules: self-prompting and analogical reasoning. Self-prompting module based on learnable description and CLIP-text encoder generates context-aware prompt by combining specific image feature; then an objectness prompt score map is produced by computing the similarity between pixel-level features and context-aware prompt. With this score map, multi-scale image features are enhanced and pixel-level features are chosen for graph construction. While for analogical reasoning module, graph nodes consists of category-level prompt nodes and pixel-level image feature nodes. Analogical inference is based graph convolution. Under the guidance of category-level nodes, different-scale object features have been enhanced, which helps achieve more accurate detection of challenging objects. Extensive experiments illustrate that SPAR outperforms traditional methods, offering a more robust and accurate solution for UAVOD.

Thermal object detection is a critical task in various fields, such as surveillance and autonomous driving. Current state-of-the-art (SOTA) models always leverage a prior Thermal-To-Visible (T2V) translation model to obtain visible spectrum information, followed by a cross-modality aggregation module to fuse information from both modalities. However, this fusion approach does not fully exploit the complementary visible spectrum information beneficial for thermal detection. To address this issue, we propose a novel cross-modal fusion method called Pseudo Visible Feature Fine-Grained Fusion (PFGF). Specifically, a graph is constructed with nodes generated from multi-level thermal features and pseudo-visual latent features produced by the T2V model. Each level of features corresponds to a subgraph. An Inter-Mamba block is proposed to perform cross-modality fusion between nodes at the lowest level; while a Cascade Knowledge Integration (CKI) strategy is used to fuse low-level fused information to high-level subgraphs in a cascade manner. After several iterations of graph node updating, each subgraph outputs an aggregated feature to the detection head respectively. Unlike previous cross-modal fusion methods, our approach explicitly models high-level relationships between cross-modal data, effectively fusing different granularity information. Experimental results demonstrate that our method achieves SOTA detection performance. Code is available at https://github.com/liting1018/PFGF.

Test-time adaptation with pre-trained vision-language models, such as CLIP, aims to adapt the model to new, potentially out-of-distribution test data. Existing methods calculate the similarity between visual embedding and learnable class embeddings, which are initialized by text embeddings, for zero-shot image classification. In this work, we first analyze this process based on Bayes theorem, and observe that the core factors influencing the final prediction are the likelihood and the prior. However, existing methods essentially focus on adapting class embeddings to adapt likelihood, but they often ignore the importance of prior. To address this gap, we propose a novel approach, Bayesian Class Adaptation (BCA), which in addition to continuously updating class embeddings to adapt likelihood, also uses the posterior of incoming samples to continuously update the prior for each class embedding. This dual updating mechanism allows the model to better adapt to distribution shifts and achieve higher prediction accuracy. Our method not only surpasses existing approaches in terms of performance metrics but also maintains superior inference rates and memory usage, making it highly efficient and practical for real-world applications.

Unmanned Aerial Vehicle (UAV) object detection faces significant challenges due to complex environmental conditions and different imaging conditions. These factors introduce significant changes in scale and appearance, particularly for small objects that occupy limited pixels and exhibit limited information, complicating detection tasks. To address these challenges, we propose a Multimodel Causal Reasoning framework based on YOLO backbone for UAV Object Detection (MCR-UOD). The key idea is to use the backdoor adjustment to discover the condition-invariant object representation for easy detection. Specifically, the YOLO backbone is first adjusted to incorporate the pre-trained vision-language model. The original category labels are replaced with semantic text prompts, and the detection head is replaced with text-image contrastive learning. Based on this backbone, our method consists of two parts. The first part, named language guided region exploration, discovers the regions with high probability of object existence using text embeddings based on vision-language model such as CLIP. Another part is the backdoor adjustment casual reasoning module, which constructs a confounder dictionary tailored to different imaging conditions to capture global image semantics and derives a prior probability distribution of shooting conditions. During causal inference, we use the confounder dictionary and the prior to intervene on local instance features, disentangling condition variations, and obtaining condition-invariant representations. Experimental results on several public datasets confirm the state-of-the-art performance of our approach. The code, data and models will be released upon publication of this paper.

We propose to explore an interesting and promising problem, Cloud Object Detector Adaptation (CODA), where the target domain leverages detections provided by a large cloud model to build a target detector. Despite with powerful generalization capability, the cloud model still cannot achieve error-free detection in a specific target domain. In this work, we present a novel Cloud Object detector adaptation method by Integrating different source kNowledge (COIN). The key idea is to incorporate a public vision-language model (CLIP) to distill positive knowledge while refining negative knowledge for adaptation by self-promotion gradient direction alignment. To that end, knowledge dissemination, separation, and distillation are carried out successively. Knowledge dissemination combines knowledge from cloud detector and CLIP model to initialize a target detector and a CLIP detector in target domain. By matching CLIP detector with the cloud detector, knowledge separation categorizes detections into three parts: consistent, inconsistent and private detections such that divide-and-conquer strategy can be used for knowledge distillation. Consistent and private detections are directly used to train target detector; while inconsistent detections are fused based on a consistent knowledge generation network, which is trained by aligning the gradient direction of inconsistent detections to that of consistent detections, because it provides a direction toward an optimal target detector. Experiment results demonstrate that the proposed COIN method achieves the state-of-the-art performance.

Summary In mobile edge computing (MEC), due to the limited computing resources and power of mobile augmented reality (MAR) devices, cache identification results which can reduce power consumption and executing time of mobile devices are the solution to process MAR tasks. In this paper, we study an allocation cache problem in MAR systems. The allocation cache problem is formulated as maximizing the cache utility of cache hit ratio and user preference factor. To solve this problem, a cache resource allocation and cache space adjustment policy for edge computing systems is proposed. We also propose an improved double deep Q‐network (DDQN) algorithm to learn this policy. Simulation results show that the policy greatly improves the cache hit ratio compared with the traditional caching policy.

Recently, Unmanned Aerial Vehicles (UAVs) have attracted much attention due to their flexibility and low cost. However, there are limitations for multiple UAVs such as limited energy and collaborative coverage. To achieve a better coverage performance, each UAV needs to find the optimal position to cover many ground users while saving energy. However, there are trade-offs between coverage utility and energy consumption. In this paper, we study a multi-UAV communication scenario where multi-UAV array is deployed to provide wireless coverage for mobile ground users. Considering the number, 3D positions, and speeds of UAVs, we formulate a Coverage Utility and Energy Multi-objective Optimization Problem (CUEMOP) to simultaneously maximize the total coverage utility and minimize the total energy consumption of UAVs. Due to the complexity and NP-hardness of the formulated CUEMOP, we propose Improved Multi-objective Grey Wolf Optimizer (ImMOGWO) algorithm. In this algorithm, we design the Role Determination (RD) algorithm to cluster the ground users and prepare for initialization of UAV number and position. Hybrid solution initialization (HSI) algorithm is to initialize multi-dimensional variables and overcome algorithm inefficiency caused by random initialization. The Levy flight and Sin Cosine method based on the MOGWO algorithm (LSCMGA) is proposed to increase the diversity of solutions and ensure the convergence effect of the algorithm. Simulation results verify that proposed ImMOGWO algorithm has better performance than some other benchmark methods.

The rapid development of edge computing has an impact on the Internet of Vehicles (IoV). However, the high-speed mobility of vehicles makes the task offloading delay unstable and unreliable. Hence, this paper studies the task offloading problem to provide stable computing, communication and storage services for user vehicles in vehicle networks. The offloading problem is formulated to minimize cost consumption under the maximum delay constraint by jointly considering the positions, speeds and computation resources of vehicles. Due to the complexity of the problem, we propose the vehicle deep Q-network (V-DQN) algorithm. In V-DQN algorithm, we firstly propose a vehicle adaptive feedback (VAF) algorithm to obtain the priority setting of processing tasks for service vehicles. Then, the V-DQN algorithm is implemented based on the result of VAF to realize task offloading strategy. Specially, the interruption problem caused by the movement of the vehicle is formulated as a return function as part of evaluating the task offloading strategy. The simulation results show that our proposed scheme significantly reduces cost consumption and improves Quality of Service (QoS).