Multi-agent multi-objective systems (MAMOS) have emerged as powerful frameworks for modelling complex decision-making problems across various real-world domains, such as robotic exploration, autonomous traffic management, and sensor network optimisation. MAMOS enhances scalability and robustness through decentralised control and more accurately captures inherent trade-offs between conflicting objectives. In MAMOS, each agent uses utility functions that map return vectors to scalar values. Existing MAMOS optimisation methods face significant challenges in handling heterogeneous objective and utility function settings, where training non-stationarity is intensified due to private utility functions and the associated policies. In this paper, we first theoretically prove that direct access to, or structured modeling of, global utility functions is necessary to achieve the Bayesian Nash Equilibrium under decentralised execution constraints. To access the global utility functions while preserving the decentralised execution, we propose an Agent-Attention Multi-Agent Multi-Objective Reinforcement Learning (AA-MAMORL) framework. Our approach implicitly learns a joint belief over other agents’ utility functions and their associated policies during centralised training, effectively mapping global states and utilities to each agent's policy. During execution, each agent independently selects actions based on local observations and its private utility function to approximate a BNE, without relying on inter-agent communication. We evaluate our framework through extensive experiments in a custom-designed MAMO Particle environment and the standard MOMALand benchmark. The results demonstrate that accessibility to global preferences and our proposed AA-MAMORL significantly improves performance and consistently outperforms state-of-the-art methods.

The integration of Artificial Intelligence (AI) within 6G networks is poised to revolutionize connectivity, reliability, and intelligent decision-making. However, the performance of AI models in these networks is crucial, as any decline can significantly impact network efficiency and the services it supports. Understanding the root causes of performance degradation is essential for maintaining optimal network functionality. In this paper, we propose a novel approach to reason about AI model performance degradation in 6G networks using the Large Language Models (LLMs) empowered Chain-of-Thought (CoT) method. Our approach employs an LLM as a “teacher” model through zero-shot prompting to generate teaching CoT rationales, followed by a CoT “student” model that is fine-tuned by the generated teaching data for learning to reason about performance declines. The efficacy of this model is evaluated in a real-world scenario involving a real-time 3D rendering task with multi-Access Technologies (mATs) including WiFi, 5G, and LiFi for data transmission. Experimental results show that our approach achieves over 97 % reasoning accuracy on the built test questions, confirming the validity of our collected dataset and the effectiveness of the LLM-CoT method. Our findings highlight the potential of LLMs in enhancing the reliability and efficiency of 6G networks, representing a significant advancement in the evolution of AI-native network infrastructures.

The adoption of Artificial Intelligence (AI) based Virtual Network Functions (VNFs) has witnessed significant growth, posing a critical challenge in orchestrating AI models within next-generation 6G networks. Finding optimal AI model placement is significantly more challenging than placing traditional software-based VNFs, due to the introduction of numerous uncertain factors by AI models, such as varying computing resource consumption, dynamic storage requirements, and changing model performance. To address the AI model placement problem under uncertainties, this paper presents a novel approach employing a sequence-to-sequence (S2S) neural network which considers uncertainty estimations. The S2S model, characterized by its encoding-decoding architecture, is designed to take the service chain with a number of AI models as input and produce the corresponding placement of each AI model. To address the introduced uncertainties, our methodology incorporates the orthonormal certificate module for uncertainty estimation and utilizes fuzzy logic for uncertainty representation, thereby enhancing the capabilities of the S2S model. Experiments demonstrate that the proposed method achieves competitive results across diverse AI model profiles, network environments, and service chain requests.

Vision-based surface defect detection for no-service rails provides a fast and effective way to monitor product quality. However, most of the existing surface defect detection algorithms${1)}$prioritize enhancing detection accuracy at the expense of processing speed and${2)}$lack compatibility with various input image types [RGB images or RGB-depth (RGBD) images]. To address these issues, we propose a skeleton-aware accurate and fast network for pixelwise surface defect detection. The skeleton is first used in defect detection tasks to aid in locating defects and to guide the growth of more accurate defect predictions by utilizing its continuity. In addition, a simple and efficient feature fusion module, information prominence fusion, is proposed for cross-layer feature representation. A compatibility module, depth-aware fusion, is devised to introduce and integrate depth information. Experiments have proven that our network can achieve excellent detection results while its detection speed can reach 537.2 fps for RGB detection and 423.8 fps for RGBD detection at 20 input batch sizes. Generalizability experiments verify that our network still performs competitively on the surface defect detection of strip steel and salient object detection of RGB and RGBD natural images.

Salient object detection (SOD) of images refers to simulating the attention mechanism of human vision to capture the most attractive objects in an image. Current SOD mainly relies on RGB images captured by optical cameras. However, existing optical cameras are not comparable to the human visual system, especially in poorly illumination scenes. Our human visual system is able to resolve scenes well in low light conditions, while optical cameras can barely image without enough illumination. To make machine vision closer to the imaging of the human eye, we propose to use thermal infrared (T) images to compensate RGB images and build a variable illumination RGBT dataset named VI-RGBT1500 for SOD. This dataset is collected under three different illumination conditions including sufficient illumination, uneven illumination and insufficient illumination to fully demonstrate the superiority of the RGBT image combination. Furthermore, we propose a multiple graph affinity interactive (MGAI) network to validate the proposed dataset. Our network structure is simple using only the MGAI to fuse the features of different modalities. Meanwhile, the MGAI model highlights valuable information during the interaction, which facilitates feature representation under variable illumination. The proposed VI-RGBT1500 dataset and three publicly available RGBT SOD datasets are used for the comparison experiments, and the results with the state-of-the-art methods prove that our VI-RGBT1500 dataset is valuable and the performance of the MGAI network is competitive. The VI-RGBT1500 dataset and the MGAI network are available at:https://github.com/huanglm-me/VI-RGBT1500.

UAVs are widely used in various industries, and various visual tasks under the perspective of the UAV have been widely studied. In particular, the RGB-T detection method based on UAVs has shown significant advantages. However, existing RGB-T methods are designed based on registration image pairs rather than detecting images directly acquired by UAVs. This detection process is limited by the accuracy of image registration. And image registration wastes a lot of time. To solve the above problems, we construct an unregistered RGB-T image salient object detection (SOD) dataset under the UAV perspective, known as UAV RGB-T 2400. The dataset includes many challenging scenes, and the images are not manually registered. Further, we construct a modality registration and object search (MROS) framework for unregistered RGB-T SOD. Firstly, a modality registration scheme is proposed to solve the unregistration problem of modal features. We successively perform pixel-level registration from a local perspective and semantic-level registration from a global perspective for different modal features. And we carry out the channel and spatial interaction for the different modal features in modality registration. Aiming at the interference problem in the UAV detection environment, we propose an object search scheme. The two high-level features are used to search the object location, and the three low-level features are used to refine the object and produce prediction results. Experimental results on the UAV RGB-T 2400 dataset show that MROS is effective compared with state-of-the-art methods. The code is available at: https://github.com/VDT-2048/UAV-RGB-T-2400.

RGB and thermal infrared (RGBT) image saliency detection is a relatively new direction in the field of computer vision. Combining the advantages of RGB images and T images can significantly improve detection performance. Currently, there are only a few methods to work on RGBT saliency detection, and the number of image samples cannot meet the training requirements for deep learning, so it remains valuable to propose an effective unsupervised method. In this paper, we present an unsupervised RGBT saliency detection method based on multi-graph fusion and learning. Firstly, RGB images and T images are adaptively fused based on boundary information to produce more accurate superpixels. Next, a multi-graph fusion model is proposed to selectively learn useful information from multi-modal images. Finally, we implement the theory of finding good neighbors in the graph affinity and propose different algorithms for two stages of saliency ranking. Experimental results on three RGBT datasets show that the proposed method is effective compared with the state-of-the-art algorithms.

RGB salient object detection (SOD) has made great progress. However, the performance of this single-modal salient object detection will be significantly decreased when encountering some challenging scenes, such as low light or darkness. To deal with the above challenges, thermal infrared (T) image is introduced into the salient object detection. This fused modal is called RGB-T salient object detection. To achieve deep mining of the unique characteristics of single modal and the full integration of cross-modality information, a novel Cross-Guided Fusion Network (CGFNet) for RGB-T salient object detection is proposed. Specifically, a Cross-Scale Alternate Guiding Fusion (CSAGF) module is proposed to mine the high-level semantic information and provide global context support. Subsequently, we design a Guidance Fusion Module (GFM) to achieve sufficient cross-modality fusion by using single modal as the main guidance and the other modal as auxiliary. Finally, the Cross-Guided Fusion Module (CGFM) is presented and serves as the main decoding block. And each decoding block is consists of two parts with two modalities information of each being the main guidance, i.e., cross-shared Cross-Level Enhancement (CLE) and Global Auxiliary Enhancement (GAE). The main difference between the two parts is that the GFM using different modalities as the main guide. The comprehensive experimental results prove that our method achieves better performance than the state-of-the-art salient detection methods. The source code has released at:https://github.com/wangjie0825/CGFNet.git.

Visual information is increasingly recognized as a useful method to detect rail surface defects due to its high efficiency and stability. However, it cannot sufficiently detect a complete defect in the complex background information. The addition of surface profiles can effectively improve this by including a 3-D information of defects. However, in high-speed detection, the traditional 3-D profile acquisition is difficult and separate from the image acquisition, which cannot satisfy the above-mentioned requirements effectively. Therefore, an unsupervised stereoscopic saliency detection method based on a binocular line-scanning system is proposed in this article. This method can simultaneously obtain a highly precise image as well as profile information while also avoids the decoding distortion of the structured light reconstruction method. In our method, a global low-rank nonnegative reconstruction algorithm with a background constraint is proposed. Unlike the low-rank recovery model, the algorithm has a more comprehensive low rank and background clustering properties. Furthermore, outlier detection based on the geometric properties of the rail surface is also proposed in this method. Finally, the image saliency results and depth outlier detection results are associated with the collaborative fusion, and a dataset (RSDDS-113) containing the rail surface defects is established for the experimental verification. The experimental results demonstrate that our method can obtain a mean absolute error of 0.09 and area under the ROC curve of 0.94, better than 15 state-of-the-art algorithms.

Saliency detection is a significant research topic in the field of image processing and computer vision. Currently, most saliency detection methods are applied to RGB images, so that they may encounter adverse scenarios characterized by complex background, inclement weather, and low illumination. Fusing complementary advantages of RGB and thermal infrared (RGB-T) images can effectively boost saliency detection performance. Therefore, we propose a novel RGB-T saliency detection method in this letter. To this end, we first regard superpixels as graph nodes and calculate the affinity matrix for each feature. Then, we propose a low-rank tensor learning model for the graph affinity, which can suppress redundant information and improve the relevance of similar image regions. Finally, a novel ranking algorithm is proposed to jointly obtain the optimal affinity matrix and saliency values under a unified structure. Test results on two RGB-T datasets illustrate the proposed method performs well when against the state-of-the-art algorithms.

Automatic discovery of topical objects from a set of image collections provides more strong cognitive capability of robot to understand the unstructured environment. In this paper, we propose a novel framework based on dictionary learning for such a task. Different from existing work which utilizes multiple segmentations to coarsely obtain the object regions, we adopt the most recently developed objectness operator to extract candidate objects. Such a method admits a great advantage that the interested objects can be more reliably segmented. A dictionary learning method is proposed to discover the topical objects. Such an optimization model exploits the observation that any image only includes a few topical objects and therefore sparsity is encouraged. Further, a globally convergent algorithm is developed to solve the dictionary learning problem and extensive experiments show that the proposed method outperforms the state-of-the-arts.