Search

The task of multi-label image classification involves recognizing multiple objects within a single image. Considering both valuable semantic information contained in the labels and essential visual features presented in the image, tight visual-linguistic interactions play a vital role in improving classification performance. Moreover, given the potential variance in object size and appearance within a single image, attention to features of different scales can help to discover possible objects in the image. Recently, Transformer-based methods have achieved great success in multi-label image classification by leveraging the advantage of modeling long-range dependencies, but they have several limitations. Firstly, existing methods treat visual feature extraction and cross-modal fusion as separate steps, resulting in insufficient visual-linguistic alignment in the joint semantic space. Additionally, they only extract visual features and perform cross-modal fusion at a single scale, neglecting objects with different characteristics. To address these issues, we propose a Hierarchical Scale-Aware Vision-Language Transformer (HSVLT) with two appealing designs: (1)~A hierarchical multi-scale architecture that involves a Cross-Scale Aggregation module, which leverages joint multi-modal features extracted from multiple scales to recognize objects of varying sizes and appearances in images. (2)~Interactive Visual-Linguistic Attention, a novel attention mechanism module that tightly integrates cross-modal interaction, enabling the joint updating of visual, linguistic and multi-modal features. We have evaluated our method on three benchmark datasets. The experimental results demonstrate that HSVLT surpasses state-of-the-art methods with lower computational cost., Comment: 10 pages, 6 figures

The deep financial turmoil in China caused by the COVID-19 pandemic has exacerbated fiscal shocks and soaring public debt levels, which raises concerns about the stability and sustainability of China's public debt growth in the future. This paper employs the Markov regime-switching model with time-varying transition probability (TVTP-MS) to investigate the growth pattern of China's public debt and the impact of financial variables such as credit, house prices and stock prices on the growth of public debt. We identify two distinct regimes of China's public debt, i.e., the surge regime with high growth rate and high volatility and the steady regime with low growth rate and low volatility. The main results are twofold. On the one hand, an increase in the growth rate of the financial variables helps to moderate the growth rate of public debt, whereas the effects differ between the two regimes. More specifically, the impacts of credit and house prices are significant in the surge regime, whereas stock prices affect public debt growth significantly in the steady regime. On the other hand, a higher growth rate of financial variables also increases the probability of public debt either staying in or switching to the steady regime. These findings highlight the necessity of aligning financial adjustments with the prevailing public debt regime when developing sustainable fiscal policies.

Based on the quarterly data from 26 advanced economies (AEs) and 18 emerging market economies (EMs) over the past two decades, this paper estimates the short- and medium-term impacts of financial cycles on the duration and amplitude of public debt cycles. The results indicate that public debt expansions are larger than their contractions in duration and amplitude, aligning with the "deficit bias hypothesis" and being more pronounced in EMs than in AEs. The impacts of various financial cycles are different. Specifically, credit cycles in EMs significantly impact the duration and amplitude of public debt cycles. Notably, short- and medium-term credit booms in EMs shorten the duration of public debt contractions and reduce the amplitude. Fast credit growth in AEs prolongs the duration of public debt expansions and increases the amplitude. However, credit cycles in AEs show no significant impact. For house price cycles, the overall impact is stronger in EMs than in AEs, differing between short- and medium-term cycles. Finally, the impact of equity price cycles is significant in the short term, but not in the medium term. Equity price busts are more likely to prolong the expansion of public debt in EMs while increasing the amplitude of public debt contractions in AEs. Uncovering the impacts of multiple financial cycles on public debt cycles provides implications for better debt policies under different financial conditions.

The deployment of the sensor nodes (SNs) always plays a decisive role in the system performance of wireless sensor networks (WSNs). In this work, we propose an optimal deployment method for practical heterogeneous WSNs which gives a deep insight into the trade-off between the reliability and deployment cost. Specifically, this work aims to provide the optimal deployment of SNs to maximize the coverage degree and connection degree, and meanwhile minimize the overall deployment cost. In addition, this work fully considers the heterogeneity of SNs (i.e. differentiated sensing range and deployment cost) and three-dimensional (3-D) deployment scenarios. This is a multi-objective optimization problem, non-convex, multimodal and NP-hard. To solve it, we develop a novel swarm-based multi-objective optimization algorithm, known as the competitive multi-objective marine predators algorithm (CMOMPA) whose performance is verified by comprehensive comparative experiments with ten other stateof-the-art multi-objective optimization algorithms. The computational results demonstrate that CMOMPA is superior to others in terms of convergence and accuracy and shows excellent performance on multimodal multiobjective optimization problems. Sufficient simulations are also conducted to evaluate the effectiveness of the CMOMPA based optimal SNs deployment method. The results show that the optimized deployment can balance the trade-off among deployment cost, sensing reliability and network reliability. The source code is available on https://github.com/iNet-WZU/CMOMPA., Comment: 25 pages

Large Vision Model (LVM) has recently demonstrated great potential for medical imaging tasks, potentially enabling image enhancement for sparse-view Cone-Beam Computed Tomography (CBCT), despite requiring a substantial amount of data for training. Meanwhile, Deep Image Prior (DIP) effectively guides an untrained neural network to generate high-quality CBCT images without any training data. However, the original DIP method relies on a well-defined forward model and a large-capacity backbone network, which is notoriously difficult to converge. In this paper, we propose a stable optimization method for the forward-model-free, LVM-based DIP model for sparse-view CBCT. Our approach consists of two main characteristics: (1) multi-scale perceptual loss (MSPL) which measures the similarity of perceptual features between the reference and output images at multiple resolutions without the need for any forward model, and (2) a reweighting mechanism that stabilizes the iteration trajectory of MSPL. One shot optimization is used to simultaneously and stably reweight MSPL and optimize LVM. We evaluate our approach on two publicly available datasets: SPARE and Walnut. The results show significant improvements in both image quality metrics and visualization that demonstrates reduced streak artifacts. The source code is available upon request., Comment: 5 pages, 4 figures, 1 table. Accepted to ICASSP 2024

In this paper, we propose a phase attention residual network (PA-ResSeg) to model multi-phase features for accurate liver tumor segmentation, in which a phase attention (PA) is newly proposed to additionally exploit the images of arterial (ART) phase to facilitate the segmentation of portal venous (PV) phase. The PA block consists of an intra-phase attention (Intra-PA) module and an inter-phase attention (Inter-PA) module to capture channel-wise self-dependencies and cross-phase interdependencies, respectively. Thus it enables the network to learn more representative multi-phase features by refining the PV features according to the channel dependencies and recalibrating the ART features based on the learned interdependencies between phases. We propose a PA-based multi-scale fusion (MSF) architecture to embed the PA blocks in the network at multiple levels along the encoding path to fuse multi-scale features from multi-phase images. Moreover, a 3D boundary-enhanced loss (BE-loss) is proposed for training to make the network more sensitive to boundaries. To evaluate the performance of our proposed PA-ResSeg, we conducted experiments on a multi-phase CT dataset of focal liver lesions (MPCT-FLLs). Experimental results show the effectiveness of the proposed method by achieving a dice per case (DPC) of 0.77.87, a dice global (DG) of 0.8682, a volumetric overlap error (VOE) of 0.3328 and a relative volume difference (RVD) of 0.0443 on the MPCT-FLLs. Furthermore, to validate the effectiveness and robustness of PA-ResSeg, we conducted extra experiments on another multi-phase liver tumor dataset and obtained a DPC of 0.8290, a DG of 0.9132, a VOE of 0.2637 and a RVD of 0.0163. The proposed method shows its robustness and generalization capability in different datasets and different backbones., Comment: A self-archive version to be published in Medical Physics, awaiting minor revision

Learning vector autoregressive models from multivariate time series is conventionally approached through least squares or maximum likelihood estimation. These methods typically assume a fully connected model which provides no direct insight to the model structure and may lead to highly noisy estimates of the parameters. Because of these limitations, there has been an increasing interest towards methods that produce sparse estimates through penalized regression. However, such methods are computationally intensive and may become prohibitively time-consuming when the number of variables in the model increases. In this paper we adopt an approximate Bayesian approach to the learning problem by combining fractional marginal likelihood and pseudo-likelihood. We propose a novel method, PLVAR, that is both faster and produces more accurate estimates than the state-of-the-art methods based on penalized regression. We prove the consistency of the PLVAR estimator and demonstrate the attractive performance of the method on both simulated and real-world data.

We investigate the learning performance of the pseudolikelihood maximization method for inverse Ising problems. In the teacher-student scenario under the assumption that the teacher's couplings are sparse and the student does not know the graphical structure, the learning curve and order parameters are assessed in the typical case using the replica and cavity methods from statistical mechanics. Our formulation is also applicable to a certain class of cost functions having locality; the standard likelihood does not belong to that class. The derived analytical formulas indicate that the perfect inference of the presence/absence of the teacher's couplings is possible in the thermodynamic limit taking the number of spins $N$ as infinity while keeping the dataset size $M$ proportional to $N$, as long as $\alpha=M/N > 2$. Meanwhile, the formulas also show that the estimated coupling values corresponding to the truly existing ones in the teacher tend to be overestimated in the absolute value, manifesting the presence of estimation bias. These results are considered to be exact in the thermodynamic limit on locally tree-like networks, such as the regular random or Erd\H{o}s--R\'enyi graphs. Numerical simulation results fully support the theoretical predictions. Additional biases in the estimators on loopy graphs are also discussed., Comment: 29 pages, 8 figures