The Direct Segment Anything Model (DirectSAM) excels in class-agnostic contour extraction. In this paper, we explore its use by applying it to optical remote sensing imagery, where semantic contour extraction—such as identifying buildings, road networks, and coastlines-holds significant practical value. Those applications are currently handled via training specialized small models separately on small datasets in each domain. We introduce a foundation model derived from DirectSAM, termed DirectSAM-RS, which not only inherits the strong segmentation capability acquired from natural images, but also benefits from a large-scale dataset we created for remote sensing semantic contour extraction. This dataset comprises over 34k image-text-contour triplets, making it at least 30 times larger than individual dataset. DirectSAM-RS integrates a prompter module: a text encoder and cross-attention layers attached to the DirectSAM architecture, which allows flexible conditioning on target class labels or referring expressions. We evaluate the DirectSAM-RS in both zero-shot and fine-tuning setting, and demonstrate that it achieves state-of-the-art performance across several downstream benchmarks.

With the rapid advancement of deep learning technologies, self-supervised learning utilizing large-scale unlabeled datasets has emerged as a dominant learning paradigm across multiple fields. This paradigm aligns well with the nature of medical imaging data, which has led to significant research efforts in applying self-supervised learning methods to this domain. However, many of these approaches fail to fully consider the unique characteristics of medical imaging, particularly the critical role that texture information plays in the diagnosis of thorax diseases. To address this gap, we propose a novel texture-aware self-supervised learning framework that leverages the Gray-Level Co-occurrence Matrix (GLCM) as an auxiliary signal to strengthen the model’s capacity to extract disease-relevant texture features. Additionally, we integrate curriculum learning into our approach, which gradually emphasizes texture information throughout the training process. This method enables the model to more effectively capture the inherent characteristics of medical imaging data. Our qualitative and quantitative experimental results show that our approach surpasses the current state-of-the-art methods on both the NIH CXR and Stanford CheXpert datasets.

The hybrid wireless and power line communication (HWPLC) networks address the problem that mobile wireless sensors and power line communication (PLC) sensors cannot communicate with each other within an Internet of Things (IoT) network. In this paper, we design a relay equipped with a dual wireless and PLC interface, which connects both the PLC and wireless sensors into an IoT network. Furthermore, the dual-interface relay forwards messages by adaptively selecting a interface according to the channel state. A general mathematical probability model of the dual-interface relaying system is presented. The probability density function of the output signal-to-noise ratio (SNR) is developed, which is based on explicit closed-form expressions derived from the statistics character of the PLC and wireless channel. Furthermore, the average capacity, bit-error rate (BER) expressions, and the outage probability formulas are derived. Numerical results show that the HPLWC relaying system with the dual-interface can significantly improve the performance of capacity, BER, and outage probability by adaptively selecting the interface with the optimal received SNR.

In heterogeneous vehicular networks, non-orthogonal multiple access (NOMA) with effective resource allocation improves spectrum efficiency by allowing multiple users to share the same channel. However, channel estimation errors caused by high mobility in vehicular networks affect system robustness and link reliability. As a result, resource allocation in high-mobility scenarios is a challenging issue. In this paper, robust resource allocation is studied to improve both the throughput performance and reliability of NOMA-based heterogeneous vehicular networks. A cascaded Hungarian channel assignment algorithm is proposed to simplify the formulated resource allocation problem with reliability requirements into a robust power allocation problem with chance constraints. With the approximation of non-central Chi-square distribution, the chance constraints are transformed into deterministic constraints. Furthermore, the optimal power allocation for the transformed problem is obtained in consideration of the requirements in NOMA. Simulation results illustrate the effectiv- eness of the proposed robust resource allocation scheme and its improvement over existing schemes.

In this paper, we study the resource allocation problem for a cooperative device-to-device (D2D)- enabled wireless caching network, where each user randomly caches popular contents to its memory and shares the contents with nearby users through D2D links. In order to enhance the throughput of spectrum-sharing D2D links, which may be severely limited by the interference among D2D links, we enable the cooperation among some of the D2D links to eliminate the interference among them. We formulate a joint link scheduling and power allocation problem to maximize the overall throughput of cooperative D2D links (CDLs) and non- cooperative D2D links (NDLs), which is NP-hard. To solve the problem, we decompose it into two sub- problems, which maximize the sum rates of the CDLs and the NDLs, respectively. For CDL optimization, we propose a semi-orthogonal-based algorithm for joint user scheduling and power allocation. For NDL optimization, we propose a novel low-complexity algorithm to perform link scheduling and develop a Difference of Convex functions (D.C.) programming method to solve the non-convex power allocation problem. Simulation results show that cooperative transmission can significantly improve both the number of served users and the overall system throughput.

In this paper, the energy efficiency in a cellular network with device-to-device communications is studied. A mixed-integer max-min optimization problem is formulated with both mode selection and resource allocation. Since the optimal solution requires an exhaustive search, a low-complexity decomposition (LCD) method is derived. A fairness-aware mode selection scheme, a subcarrier assignment scheme, and a mode switching scheme are introduced and analyzed. Moreover, a novel power allocation scheme is proposed, which exploits the property of the fractional structure of the energy efficiency optimization problem over multiple subcarriers. The proposed LCD method is scalable and suitable for a large number of users and subcarriers. Simulation results demonstrate that our proposed LCD method achieves satisfactory energy efficiency performance and promotes the fairness among individual users.

In heterogeneous vehicular networks, power control with non-orthogonal multiple access (NOMA) is effective in improving spectrum efficiency by allowing multiple users to share the same channel. However, the channel estimation error caused by high mobility in vehicular communications needs to be considered for efficient power allocation and link reliability. In this paper, a robust power allocation problem with chance constraints is studied to improve at the same time the throughput performance and reliability of NOMA heterogeneous vehicular communications. Through the approximation of non-central Chi-square distribution, the chance constraints are transformed into deterministic constraints. Moreover, the optimal power allocation is obtained with the consideration of NOMA requirements. Simulation results illustrate the effectiveness of the proposed power allocation and its improvement over existing schemes.

In this paper, we study resource allocation in full-duplex OFDMA networks. We explore the joint optimization of subcarrier assignment, uplink-downlink user pairing, and power allocation to maximize the overall throughput with consideration of self-interference and inter-node interference. By using the dual method, we can decompose the original optimization problem into a primal problem and a dual problem. We adopt the concave-convex procedure to transform the primal problem into a tractable form through sequential convex approximations while we utilize the sub-gradient method to solve the dual problem. Simulation results show that the proposed algorithm can always achieve better throughput in comparison with the existing algorithms.

In this paper, the energy-efficient design of wireless relay networks with radio frequency (RF) energy harvesting capability is studied. A decode-and-forward relay is used to forward information and harvest energy simultaneously from the same signal with a power splitting architecture. Given the power and quality-of-service constraints, a non- convex energy- efficient optimization problem is formulated, in which the transmit power and power splitting ratio are coupled together. With our proposed algorithm, the problem is decoupled and solved. The question of when RF energy harvesting relay is preferred is also discussed. Simulation results demonstrate that the proposed algorithm improves the energy efficiency over the power allocation scheme for capacity maximization. The RF energy harvesting relay is shown to be preferred over the direct transmission when the environmental noise level is high.