Optical Remote Sensing Image Understanding with Weak Supervision: Concepts, Methods, and Perspectives

In recent years, supervised learning has been widely used in various tasks of optical remote sensing image understanding, including remote sensing image classification, pixel-wise segmentation, change detection, and object detection. The methods based on supervised learning need a large amount of high-quality training data and their performance highly depends on the quality of the labels. However, in practical remote sensing applications, it is often expensive and time-consuming to obtain large-scale data sets with high-quality labels, which leads to a lack of sufficient supervised information. In some cases, only coarse-grained labels can be obtained, resulting in the lack of exact supervision. In addition, the supervised information obtained manually may be wrong, resulting in a lack of accurate supervision. Therefore, remote sensing image understanding often faces the problems of incomplete, inexact, and inaccurate supervised information, which will affect the breadth and depth of remote sensing applications. In order to solve the above-mentioned problems, researchers have explored various tasks in remote sensing image understanding under weak supervision. This paper summarizes the research progress of weakly supervised learning in the field of remote sensing, including three typical weakly supervised paradigms: 1) Incomplete supervision, where only a subset of training data is labeled; 2) Inexact supervision, where only coarse-grained labels of training data are given; 3) Inaccurate supervision, where the labels given are not always true on the ground.

Performance Analysis of Wireless Network Aided by Discrete-Phase-Shifter IRS

Discrete phase shifters of intelligent reflecting surface (IRS) generates phase quantization error (QE) and degrades the receive performance at the receiver. To make an analysis of the performance loss caused by IRS with phase QE, based on the law of large numbers, the closed-form expressions of signal-to-noise ratio (SNR) performance loss (PL), achievable rate (AR), and bit error rate (BER) are successively derived under line-of-sight (LoS) channels and Rayleigh channels. Moreover, based on the Taylor series expansion, the approximate simple closed form of PL of IRS with approximate QE is also given. The simulation results show that the performance losses of SNR and AR decrease as the number of quantization bits increase, while they gradually increase with the number of IRS phase shifter elements increase. Regardless of LoS channels or Rayleigh channels, when the number of quantization bits is larger than or equal to 3, the performance losses of SNR and AR are less than 0.23dB and 0.08bits/s/Hz, respectively, and the BER performance degradation is trivial. In particular, the performance loss difference between IRS with QE and IRS with approximate QE is negligible when the number of quantization bits is not less than 2.

A3CLNN: Spatial, Spectral and Multiscale Attention ConvLSTM Neural Network for Multisource Remote Sensing Data Classification

The problem of effectively exploiting the information multiple data sources has become a relevant but challenging research topic in remote sensing. In this paper, we propose a new approach to exploit the complementarity of two data sources: hyperspectral images (HSIs) and light detection and ranging (LiDAR) data. Specifically, we develop a new dual-channel spatial, spectral and multiscale attention convolutional long short-term memory neural network (called dual-channel A3CLNN) for feature extraction and classification of multisource remote sensing data. Spatial, spectral and multiscale attention mechanisms are first designed for HSI and LiDAR data in order to learn spectral- and spatial-enhanced feature representations, and to represent multiscale information for different classes. In the designed fusion network, a novel composite attention learning mechanism (combined with a three-level fusion strategy) is used to fully integrate the features in these two data sources. Finally, inspired by the idea of transfer learning, a novel stepwise training strategy is designed to yield a final classification result. Our experimental results, conducted on several multisource remote sensing data sets, demonstrate that the newly proposed dual-channel A3CLNN exhibits better feature representation ability (leading to more competitive classification performance) than other state-of-the-art methods.

MC-UNet Multi-module Concatenation based on U-shape Network for Retinal Blood Vessels Segmentation

Accurate segmentation of the blood vessels of the retina is an important step in clinical diagnosis of ophthalmic diseases. Many deep learning frameworks have come up for retinal blood vessels segmentation tasks. However, the complex vascular structure and uncertain pathological features make the blood vessel segmentation still very challenging. A novel U-shaped network named Multi-module Concatenation which is based on Atrous convolution and multi-kernel pooling is put forward to retinal vessels segmentation in this paper. The proposed network structure retains three layers the essential structure of U-Net, in which the atrous convolution combining the multi-kernel pooling blocks are designed to obtain more contextual information. The spatial attention module is concatenated with dense atrous convolution module and multi-kernel pooling module to form a multi-module concatenation. And different dilation rates are selected by cascading to acquire a larger receptive field in atrous convolution. Adequate comparative experiments are conducted on these public retinal datasets: DRIVE, STARE and CHASE_DB1. The results show that the proposed method is effective, especially for microvessels. The code will be put out at https://github.com/Rebeccala/MC-UNet

Semi-Data-Aided Channel Estimation for MIMO Systems via Reinforcement Learning

Data-aided channel estimation is a promising solution to improve channel estimation accuracy by exploiting data symbols as pilot signals for updating an initial channel estimate. In this paper, we propose a semi-data-aided channel estimator for multiple-input multiple-output communication systems. Our strategy is to leverage reinforcement learning (RL) for selecting reliable detected symbols among the symbols in the first part of transmitted data block. This strategy facilitates an update of the channel estimate before the end of data block transmission and therefore achieves a significant reduction in communication latency compared to conventional data-aided channel estimation approaches. Towards this end, we first define a Markov decision process (MDP) which sequentially decides whether to use each detected symbol as an additional pilot signal. We then develop an RL algorithm to efficiently find the best policy of the MDP based on a Monte Carlo tree search approach. In this algorithm, we exploit the a-posteriori probability for approximating both the optimal future actions and the corresponding state transitions of the MDP and derive a closed-form expression for the best policy. Simulation results demonstrate that the proposed channel estimator effectively mitigates both channel estimation error and detection performance loss caused by insufficient pilot signals.

Throughput Maximization for UAV-enabled Integrated Periodic Sensing and Communication

Unmanned aerial vehicle (UAV) is expected to revolutionize the existing integrated sensing and communication (ISAC) system and promise a more flexible joint design. Nevertheless, the existing works on ISAC mainly focus on exploring the performance of both functionalities simultaneously during the entire considered period, which may ignore the practical asymmetric sensing and communication requirements. In particular, always forcing sensing along with communication may make it is harder to balance between these two functionalities due to shared spectrum resources and limited transmit power. To address this issue, we propose a new integrated periodic sensing and communication mechanism for the UAV-enabled ISAC system to provide a more flexible trade-off between two integrated functionalities. Specifically, the system achievable rate is maximized via jointly optimizing UAV trajectory, user association, target sensing selection, and transmit beamforming, while meeting the sensing frequency and beam pattern gain requirement for the given targets. Despite that this problem is highly non-convex and involves closely coupled integer variables, we derive the closed-form optimal beamforming vector to dramatically reduce the complexity of beamforming design, and present a tight lower bound of the achievable rate to facilitate UAV trajectory design. Based on the above results, we propose a penalty-based algorithm to efficiently solve the considered problem. The optimal achievable rate and the optimal UAV location are analyzed under a special case of infinity number of antennas. Furthermore, we prove the structural symmetry between the optimal solutions in different ISAC frames without location constraints and propose an efficient algorithm for solving the problem with location constraints.

Energy-Efficient IRS-Aided NOMA Beamforming for 6G Wireless Communications

This manuscript presents an energy-efficient alternating optimization framework based on intelligent reflective surfaces (IRS) aided non-orthogonal multiple access beamforming (NOMA-BF) system for 6G wireless communications. Specifically, this work proposes a centralized IRS-enabled design for the NOMA-BF system to optimize the active beamforming and power allocation coefficient (PAC) of users at the transmitter in the first stage and passive beamforming at IRS in the 2nd stage to maximize the energy efficiency (EE) of the network. However, an increment in the number of supportable users with the NOMA-BF system will lead to NOMA user interference and inter-cluster interference (ICI). To mitigate the effect of ICI, first zero-forcing beamforming along with efficient user clustering algorithm is exploited and then NOMA user interference is tackled efficiently through a proposed iterative algorithm that computes PAC of NOMA user through simplified closed-form expression under the required system constraints. In the 2nd stage, the problem of passive beamforming is solved through a technique based on difference-of-convex (DC) programming and successive convex approximation (SCA). Simulation results demonstrate that the proposed alternating framework for energy-efficient IRS-assisted NOMA-BF system can achieve convergence within a few iterations and provide efficient performance in terms of EE of the system with low complexity.

Federated Learning-Based Localization with Heterogeneous Fingerprint Database

Fingerprint-based localization plays an important role in indoor location-based services, where the position information is usually collected in distributed clients and gathered in a centralized server. However, the overloaded transmission as well as the potential risk of divulging private information burdens the application.Owning the ability to address these challenges, federated learning (FL)-based fingerprinting localization comes into people's sights, which aims to train a global model while keeping raw data locally. However, in distributed machine learning (ML) scenarios, the unavoidable database heterogeneity usually degrades the performance of existing FL-based localization algorithm (FedLoc). In this paper, we first characterize the database heterogeneity with a computable metric, i.e., the area of convex hull, and verify it by experimental results. Then, a novel heterogeneous FL-based localization algorithm with the area of convex hull-based aggregation (FedLoc-AC) is proposed. Extensive experimental results, including real-word cases are conducted. We can conclude that the proposed FedLoc-AC can achieve an obvious prediction gain compared to FedLoc in heterogeneous scenarios and has almost the same prediction error with it in homogeneous scenarios. Moreover, the extension of FedLoc-AC in multi-floor cases is proposed and verified.

Nested Collaborative Learning for Long-Tailed Visual Recognition

The networks trained on the long-tailed dataset vary remarkably, despite the same training settings, which shows the great uncertainty in long-tailed learning. To alleviate the uncertainty, we propose a Nested Collaborative Learning (NCL), which tackles the problem by collaboratively learning multiple experts together. NCL consists of two core components, namely Nested Individual Learning (NIL) and Nested Balanced Online Distillation (NBOD), which focus on the individual supervised learning for each single expert and the knowledge transferring among multiple experts, respectively. To learn representations more thoroughly, both NIL and NBOD are formulated in a nested way, in which the learning is conducted on not just all categories from a full perspective but some hard categories from a partial perspective. Regarding the learning in the partial perspective, we specifically select the negative categories with high predicted scores as the hard categories by using a proposed Hard Category Mining (HCM). In the NCL, the learning from two perspectives is nested, highly related and complementary, and helps the network to capture not only global and robust features but also meticulous distinguishing ability. Moreover, self-supervision is further utilized for feature enhancement. Extensive experiments manifest the superiority of our method with outperforming the state-of-the-art whether by using a single model or an ensemble.

Collaborative Intelligent Reflecting Surface Networks with Multi-Agent Reinforcement Learning

Intelligent reflecting surface (IRS) is envisioned to be widely applied in future wireless networks. In this paper, we investigate a multi-user communication system assisted by cooperative IRS devices with the capability of energy harvesting. Aiming to maximize the long-term average achievable system rate, an optimization problem is formulated by jointly designing the transmit beamforming at the base station (BS) and discrete phase shift beamforming at the IRSs, with the constraints on transmit power, user data rate requirement and IRS energy buffer size. Considering time-varying channels and stochastic arrivals of energy harvested by the IRSs, we first formulate the problem as a Markov decision process (MDP) and then develop a novel multi-agent Q-mix (MAQ) framework with two layers to decouple the optimization parameters. The higher layer is for optimizing phase shift resolutions, and the lower one is for phase shift beamforming and power allocation. Since the phase shift optimization is an integer programming problem with a large-scale action space, we improve MAQ by incorporating the Wolpertinger method, namely, MAQ-WP algorithm to achieve a sub-optimality with reduced dimensions of action space. In addition, as MAQ-WP is still of high complexity to achieve good performance, we propose a policy gradient-based MAQ algorithm, namely, MAQ-PG, by mapping the discrete phase shift actions into a continuous space at the cost of a slight performance loss. Simulation results demonstrate that the proposed MAQ-WP and MAQ-PG algorithms can converge faster and achieve data rate improvements of 10.7% and 8.8% over the conventional multi-agent DDPG, respectively.