Abstract. Inverse scattering in layered media has a wide range of applications; examples include geophysical exploration, medical imaging, and remote sensing. In this paper, we develop a selective focusing method for identifying multiple unknown buried scatterers in a layered medium. The method is derived through an asymptotic analysis of the time reversal operator using the layered Green’s function and limited aperture measurements. We begin by showing the global focusing property of the time reversal operator. Then we demonstrate that each small sound-soft particle gives rise to one significant eigenvalue of the time reversal operator, while each sound-hard particle gives rise to three. The associated eigenfunction generates an incident wave that focuses selectively on the corresponding unknown particle. Finally, we employ the time reversal method as an initial indicator and propose an effective Bayesian inversion scheme to reconstruct multiple buried extended scatterers for enhanced resolution. Numerical experiments are provided to demonstrate the efficiency.

Advanced cognition can be measured from the human brain using brain-computer interfaces (BCIs). Integrating these interfaces with computer vision techniques, which possess efficient feature extraction capabilities, can achieve more robust and accurate detection of dim targets in aerial images. However, existing target detection methods primarily concentrate on homogeneous data, lacking efficient and versatile processing capabilities for heterogeneous multimodal data. In this article, we first build a brain-eye-computer-based object detection system for aerial images under few-shot conditions. This system detects suspicious targets using region proposal networks (RPNs), evokes the event-related potential (ERP) signal in electroencephalogram (EEG) through the eye-tracking-based slow serial visual presentation (ESSVP) paradigm, and constructs the EEG-image data pairs with eye movement data. Then, an adaptive modality balanced online knowledge distillation (AMBOKD) method is proposed to recognize dim objects with the EEG-image data. AMBOKD fuses EEG and image features using a multihead attention module, establishing a new modality with comprehensive features. To enhance the performance and robust capability of the fusion modality, simultaneous training and mutual learning between modalities are enabled by end-to-end online KD (OKD). During the learning process, an adaptive modality balancing module is proposed to ensure multimodal equilibrium by dynamically adjusting the weights of the importance and the training gradients across various modalities. The effectiveness and superiority of our method are demonstrated by comparing it with existing state-of-the-art methods. Additionally, experiments conducted on public datasets and real-world scenarios demonstrate the reliability and practicality of the proposed system and the designed method. The dataset and the source code can be found at: https://github.com/lizixing23/AMBOKD.

Abstract Multi-agent credit assignment is a research hotspot in the field of cooperative multi-agent reinforcement learning, and its key is how to accurately measure the individual contribution of each agent in the system to promote multi-agent cooperation. Existing solutions mainly use value function factorization or intrinsic reward mechanism, each of which has its own limitations, and both of them utilize global state information, which is not consistent with the information conditions in the actual confrontation. Therefore, this paper proposes a novel value factorization method for multi-agent deep reinforcement learning, which can solve the problem of credit assignment without using global state information. Our method establishes an explicit individual contribution evaluation mechanism for each agent, which portrays the role of each agent in the system by comparing the differences of joint value functions under different information conditions, so that more important agents get more attention, so as to improve the cooperative ability of agents. Experimental results show that our method outperforms all baselines in terms of learning efficiency and stability in multiple scenarios of StarCraft II, and its performance is comparable to that of the method based on global state information in easy scenarios.

The simulation of seismic wave propagation through the solution of wave equations is considered one of the fundamental topics in applied geophysics. Physics-informed neural networks (PINNs) have been widely used in geophysics as an alternative to traditional numerical methods for solving wave equations. In this work, we introduce a novel deep-learning-based framework named particle weak-form-based neural networks (ParticleWNN) to achieve better wavefield solutions in seismic modeling. The ParticleWNN is developed for solving partial differential equations (PDEs) in the weak form where the trial space is the space of deep neural networks (DNNs) and the test space is constructed by functions compactly supported in small regions. Compared with vanilla PINN, ParticleWNN offers several advantages, such as requiring less regularity, allowing local training, and parallel implementation via domain decomposition. The efficiency and accuracy of the proposed method in simulating seismic wave propagation are demonstrated by several numerical examples.

Image-based ground-to-aerial geo-localization aims to determine the geo-location of a ground query image by matching it with a large geo-tagged aerial image database. Due to the drastic difference between ground and aerial views, achieving high-accuracy geo-localization remains a huge challenge, especially in practical scenarios where ground query images have unknown orientations and even limited field-of-views (FoV). The incomplete information significantly hampers the process of learning discriminative features for image matching. In this article, we propose a novel automatic progressive learning (AMPLE) method for the orientation unknown geo-localization task. Specifically, we design a ConvNeXt-based network to effectively extract orientation-aware features from the two views. We then present two progressive training strategies without manually predefined training stages to promote the learning process. The first adaptively mines harder negative samples that contribute more to the loss, by automatically discarding redundant samples as the current best accuracy increases. The second leverages the proposed alignment-correlation hybrid (ACH) loss to guide model optimization in a progressive manner, gradually reducing the reliance on auxiliary orientation information. Extensive experiments on two benchmark datasets demonstrate that AMPLE outperforms state-of-the-art methods in orientation unknown, FoV limited, and cross-area tasks. Finally, we propose the concept of unifying unknown orientation tasks at different FoVs and show the cross-FoV generalization capability of our method.

Automated object detection in aerial images is crucial in both civil and military applications. Existing computer vision-based object detection methods are not robust enough to precisely detect dim objects in aerial images due to the cluttered backgrounds, various observing angles, small object scales, and severe occlusions. Recently, electroencephalography (EEG)-based object detection methods have received increasing attention owing to the advanced cognitive capabilities of human vision. However, how to combine the human intelligence with computer intelligence to achieve robust dim object detection is still an open question. In this paper, we propose a novel approach to efficiently fuse and exploit the properties of multi-modal data for dim object detection. Specifically, we first design a brain-computer interface (BCI) paradigm called eye-tracking-based slow serial visual presentation (ESSVP) to simultaneously collect the paired EEG and image data when subjects search for the dim objects in aerial images. Then, we develop an attention-based multi-modal fusion network to selectively aggregate the learned features of EEG and image modalities. Furthermore, we propose an adaptive multi-teacher knowledge distillation method to efficiently train the multi-modal dim object detector for better performance. To evaluate the effectiveness of our method, we conduct extensive experiments on the collected dataset in subject-dependent and subject-independent tasks. The experimental results demonstrate that the proposed dim object detection method exhibits superior effectiveness and robustness compared to the baselines and the state-of-the-art methods.

Image based 3 Degrees-of-Freedom (DoF) cross-view geo-localization aims to estimate the position and orientation of a camera on the ground by matching the captured ground image with geo-tagged aerial images. However, most existing methods do not sufficiently exploit the difference between positive and negative samples for feature extraction, resulting in low localization accuracy. In this paper, we propose a novel method called HADGEO for accurate 3-DoF cross-view geo-localization. Specifically, we design a double-siamese structure with All Learnable Fully Convolutional Networks (ALFCN) to separately extract features from the aerial and ground images. To tap full potential of our network, we define a new weighted soft-margin triplet loss by integrating the Hard Sample Mining (HSM) strategy. This loss increases the training difficulty, forcing the network to be more discriminative for orientation-aware features. A series of experiments demonstrate that our method outperforms existing methods and achieves state-of-the-art performance on orientation unknown and Field-of-View (FoV) limited conditions, further improving the accuracy of 3-DoF geo-localization.

Abstract Value factorization is a popular method for cooperative multi-agent deep reinforcement learning. In this method, agents generally have the same ability and rely only on individual value function to select actions, which is calculated from total environment reward. It ignores the impact of individual characteristics of heterogeneous agents on actions selection, which leads to the lack of pertinence during training and the increase of difficulty in learning effective policies. In order to stimulate individual awareness of heterogeneous agents and improve their learning efficiency and stability, we propose a novel value factorization method based on Personality Characteristics, PCQMIX, which assigns personality characteristics to each agent and takes them as internal rewards to train agents. As a result, PCQMIX can generate heterogeneous agents with specific personality characteristics suitable for specific scenarios. Experiments show that PCQMIX generates agents with stable personality characteristics and outperforms all baselines in multiple scenarios of the StarCraft II micromanagement task.

Abstract In order to solve the incalculability caused by the issue of inconsistent objective functions in multi-agent deep reinforcement learning, the concept of Nash equilibrium is introduced. However, a Marko game may have multiple equilibriums, how to filter out a stable and optimal one is worth studying. Besides solution concept, how to keep the balance between exploration and exploitation is another key issue in reinforcement learning. On basis of the methods, which can converge to Nash equilibrium, this paper makes improvement through Pareto optimization. In order to alleviate the problem of over fitting caused by Pareto optimization and non-convergence caused by strategy change, we use stratified sampling in place of random sampling as assistance. What’s more, our methods are trained through fictitious self-play to make full of self-learning experiences. By analyzing the experiment carried out on MAgent platform, the proposed methods are not only far better than traditional methods, but also reaching or even surpassing the state of art MADRL methods.

Quantitative viral outgrowth assays (QVOA) use limiting dilutions of CD4+ T cells to measure the size of the latent HIV-1 reservoir, a major obstacle to curing HIV-1. Efforts to reduce the reservoir require assays that can reliably quantify its size in blood and tissues. Although QVOA is regarded as a "gold standard" for reservoir measurement, little is known about its accuracy and precision or about how cell storage conditions or laboratory-specific practices affect results. Owing to this lack of knowledge, confidence intervals around reservoir size estimates-as well as judgments of the ability of therapeutic interventions to alter the size of the replication-competent but transcriptionally inactive latent reservoir-rely on theoretical statistical assumptions about dilution assays. To address this gap, we have carried out a Bayesian statistical analysis of QVOA reliability on 75 split samples of peripheral blood mononuclear cells (PBMC) from 5 antiretroviral therapy (ART)-suppressed participants, measured using four different QVOAs at separate labs, estimating assay precision and the effect of frozen cell storage on estimated reservoir size. We found that typical assay results are expected to differ from the true value by a factor of 1.6 to 1.9 up or down. Systematic assay differences comprised a 24-fold range between the assays with highest and lowest scales, likely reflecting differences in viral outgrowth readout and input cell stimulation protocols. We also found that controlled-rate freezing and storage of samples did not cause substantial differences in QVOA compared to use of fresh cells (95% probability of < 2-fold change), supporting continued use of frozen storage to allow transport and batched analysis of samples. Finally, we simulated an early-phase clinical trial to demonstrate that batched analysis of pre- and post-therapy samples may increase power to detect a three-fold reservoir reduction by 15 to 24 percentage points.

This paper concerns an inverse elastic scattering problem which is to determine the location and the shape of a rigid obstacle from the phased or phaseless far-field data for a single incident plane wave. By introducing the Helmholtz decomposition, the model problem is reduced to a coupled boundary value problem of the Helmholtz equations. The relation is established between the compressional or shear far-field pattern for the elastic wave equation and the corresponding far-field pattern for the coupled Helmholtz equations. An efficient and accurate Nyström-type discretization for the boundary integral equation is developed to solve the coupled system. The translation invariance of the phaseless compressional and shear far-field patterns are proved. A system of nonlinear integral equations is proposed and two iterative reconstruction methods are developed for the inverse problem. In particular, for the phaseless data, a reference ball technique is introduced to the scattering system in order to break the translation invariance. Numerical experiments are presented to demonstrate the effectiveness and robustness of the proposed method.