-
Learning shared template representation with augmented feature for multi-object pose estimation Neural Netw. (IF 7.8) Pub Date : 2024-04-30 Qifeng Luo, Ting-Bing Xu, Fulin Liu, Tianren Li, Zhenzhong Wei
-
Channel reflection: Knowledge-driven data augmentation for EEG-based brain–computer interfaces Neural Netw. (IF 7.8) Pub Date : 2024-04-29 Ziwei Wang, Siyang Li, Jingwei Luo, Jiajing Liu, Dongrui Wu
-
DCDLN: A densely connected convolutional dynamic learning network for malaria disease diagnosis Neural Netw. (IF 7.8) Pub Date : 2024-04-29 Zhijun Zhang, Cheng Ding, Mingyang Zhang, YaMei Luo, Jiajie Mai
-
Long-term causal effects estimation via latent surrogates representation learning Neural Netw. (IF 7.8) Pub Date : 2024-04-29 Ruichu Cai, Weilin Chen, Zeqin Yang, Shu Wan, Chen Zheng, Xiaoqing Yang, Jiecheng Guo
Estimating long-term causal effects based on short-term surrogates is a significant but challenging problem in many real-world applications such as marketing and medicine. Most existing methods estimate causal effects in an idealistic and simplistic manner — disregarding unobserved surrogates and treating all short-term outcomes as surrogates. However, such methods are not well-suited to real-world
-
High-performance deep spiking neural networks via at-most-two-spike exponential coding Neural Netw. (IF 7.8) Pub Date : 2024-04-27 Yunhua Chen, Ren Feng, Zhimin Xiong, Jinsheng Xiao, Jian K. Liu
-
Multimodal information bottleneck for deep reinforcement learning with multiple sensors Neural Netw. (IF 7.8) Pub Date : 2024-04-27 Bang You, Huaping Liu
Reinforcement learning has achieved promising results on robotic control tasks but struggles to leverage information effectively from multiple sensory modalities that differ in many characteristics. Recent works construct auxiliary losses based on reconstruction or mutual information to extract joint representations from multiple sensory inputs to improve the sample efficiency and performance of reinforcement
-
Adaptive penalty-based neurodynamic approach for nonsmooth interval-valued optimization problem Neural Netw. (IF 7.8) Pub Date : 2024-04-26 Linhua Luan, Xingnan Wen, Yuhan Xue, Sitian Qin
The complex and diverse practical background drives this paper to explore a new neurodynamic approach (NA) to solve nonsmooth interval-valued optimization problems (IVOPs) constrained by interval partial order and more general sets. On the one hand, to deal with the uncertainty of interval-valued information, the LU-optimality condition of IVOPs is established through a deterministic form. On the other
-
TGIN: Document-level event extraction with two-phase graph inference network Neural Netw. (IF 7.8) Pub Date : 2024-04-25 Yu Zhong, Bo Shen, Tao Wang
-
Salience Interest Option: Temporal abstraction with salience interest functions Neural Netw. (IF 7.8) Pub Date : 2024-04-25 Xianchao Zhu, Liang Zhao, William Zhu
Reinforcement Learning (RL) is a significant machine learning subfield that emphasizes learning actions based on environment to obtain optimal behavior policy. RL agents can make decisions at variable time scales in the form of temporal abstractions, also known as options. The issue of discovering options has seen a considerable research effort. Most notably, the Interest Option Critic (IOC) algorithm
-
Towards complex dynamic physics system simulation with graph neural ordinary equations Neural Netw. (IF 7.8) Pub Date : 2024-04-25 Guangsi Shi, Daokun Zhang, Ming Jin, Shirui Pan, Philip S. Yu
The great learning ability of deep learning facilitates us to comprehend the real physical world, making learning to simulate complicated particle systems a promising endeavour both in academia and industry. However, the complex laws of the physical world pose significant challenges to the learning based simulations, such as the varying spatial dependencies between interacting particles and varying
-
Life regression based patch slimming for vision transformers Neural Netw. (IF 7.8) Pub Date : 2024-04-25 Jiawei Chen, Lin Chen, Jiang Yang, Tianqi Shi, Lechao Cheng, Zunlei Feng, Mingli Song
Vision transformers have achieved remarkable success in computer vision tasks by using multi-head self-attention modules to capture long-range dependencies within images. However, the high inference computation cost poses a new challenge. Several methods have been proposed to address this problem, mainly by slimming patches. In the inference stage, these methods classify patches into two classes, one
-
Online continual decoding of streaming EEG signal with a balanced and informative memory buffer Neural Netw. (IF 7.8) Pub Date : 2024-04-25 Tiehang Duan, Zhenyi Wang, Fang Li, Gianfranco Doretto, Donald A. Adjeroh, Yiyi Yin, Cui Tao
Electroencephalography (EEG) based Brain Computer Interface (BCI) systems play a significant role in facilitating how individuals with neurological impairments effectively interact with their environment. In real world applications of BCI system for clinical assistance and rehabilitation training, the EEG classifier often needs to learn on sequentially arriving subjects in an online manner. As patterns
-
Blinding and blurring the multi-object tracker with adversarial perturbations Neural Netw. (IF 7.8) Pub Date : 2024-04-25 Haibo Pang, Rongqi Ma, Jie Su, Chengming Liu, Yufei Gao, Qun Jin
-
A Joint Time-Frequency Domain Transformer for multivariate time series forecasting Neural Netw. (IF 7.8) Pub Date : 2024-04-25 Yushu Chen, Shengzhuo Liu, Jinzhe Yang, Hao Jing, Wenlai Zhao, Guangwen Yang
In order to enhance the performance of Transformer models for long-term multivariate forecasting while minimizing computational demands, this paper introduces the Joint Time-Frequency Domain Transformer (JTFT). JTFT combines time and frequency domain representations to make predictions. The frequency domain representation efficiently extracts multi-scale dependencies while maintaining sparsity by utilizing
-
FPGA-based fast bin-ratio spiking ensemble network for radioisotope identification Neural Netw. (IF 7.8) Pub Date : 2024-04-24 Shouyu Xie, Edward Jones, Siru Zhang, Edward Marsden, Ian Baistow, Steve Furber, Srinjoy Mitra, Alister Hamilton
In this work, we demonstrate the training, conversion, and implementation flow of an FPGA-based bin-ratio ensemble spiking neural network applied for radioisotope identification. The combination of techniques including learned step quantisation (LSQ) and pruning facilitated the implementation by compressing the network’s parameters down to 30% yet retaining the accuracy of 97.04% with an accuracy loss
-
On the Kolmogorov neural networks Neural Netw. (IF 7.8) Pub Date : 2024-04-22 Aysu Ismayilova, Vugar E. Ismailov
In this paper, we show that the Kolmogorov two hidden layer neural network model with a continuous, discontinuous bounded and unbounded activation function in the second hidden layer can precisely represent continuous, discontinuous bounded and all unbounded multivariate functions, respectively.
-
Solving the non-submodular network collapse problems via Decision Transformer Neural Netw. (IF 7.8) Pub Date : 2024-04-21 Kaili Ma, Han Yang, Shanchao Yang, Kangfei Zhao, Lanqing Li, Yongqiang Chen, Junzhou Huang, James Cheng, Yu Rong
Given a graph , the network collapse problem (NCP) selects a vertex subset of minimum cardinality from such that the difference in the values of a given measure function is greater than a predefined collapse threshold. Many graph analytic applications can be formulated as NCPs with different measure functions, which often pose a significant challenge due to their NP-hard nature. As a result, traditional
-
Multi-scale full spike pattern for semantic segmentation Neural Netw. (IF 7.8) Pub Date : 2024-04-20 Qiaoyi Su, Weihua He, Xiaobao Wei, Bo Xu, Guoqi Li
Spiking neural networks (SNNs), as the brain-inspired neural networks, encode information in spatio-temporal dynamics. They have the potential to serve as low-power alternatives to artificial neural networks (ANNs) due to their sparse and event-driven nature. However, existing SNN-based models for pixel-level semantic segmentation tasks suffer from poor performance and high memory overhead, failing
-
The role of directed cycles in a directed neural network Neural Netw. (IF 7.8) Pub Date : 2024-04-19 Qinrui Dai, Jin Zhou, Zhengmin Kong
This paper investigates the dynamics of a directed acyclic neural network by edge adding control. We find that the local stability and Hopf bifurcation of the controlled network only depend on the size and intersection of directed cycles, instead of the number and position of the added edges. More specifically, if there is no cycle in the controlled network, the local dynamics of the network will remain
-
Span-based few-shot event detection via aligning external knowledge Neural Netw. (IF 7.8) Pub Date : 2024-04-18 Tongtao Ling, Lei Chen, Yutao Lai, Hai-Lin Liu
-
Ensuring spatial scalability with temporal-wise spatial attentive pooling for temporal action detection Neural Netw. (IF 7.8) Pub Date : 2024-04-18 Ho-Joong Kim, Seong-Whan Lee
Recent temporal action detection models have focused on end-to-end trainable approaches to utilize the representational power of backbone networks. Despite the advantages of end-to-end trainable methods, these models still employ a small spatial resolution (e.g., 96 × 96) due to the inefficient trade-off between computational cost and spatial resolution. In this study, we argue that a simple pooling
-
TFRS: A task-level feature rectification and separation method for few-shot video action recognition Neural Netw. (IF 7.8) Pub Date : 2024-04-17 Yanfei Qin, Baolin Liu
Few-shot video action recognition (FS-VAR) is a challenging task that requires models to have significant expressive power in order to identify previously unseen classes using only a few labeled examples. However, due to the limited number of support samples, the model’s performance is highly sensitive to the distribution of the sampled data. The representativeness of the support data is insufficient
-
Decentralized stochastic sharpness-aware minimization algorithm Neural Netw. (IF 7.8) Pub Date : 2024-04-17 Simiao Chen, Xiaoge Deng, Dongpo Xu, Tao Sun, Dongsheng Li
In recent years, distributed stochastic algorithms have become increasingly useful in the field of machine learning. However, similar to traditional stochastic algorithms, they face a challenge where achieving high fitness on the training set does not necessarily result in good performance on the test set. To address this issue, we propose to use of a distributed network topology to improve the generalization
-
Multi-modal long document classification based on Hierarchical Prompt and Multi-modal Transformer Neural Netw. (IF 7.8) Pub Date : 2024-04-16 Tengfei Liu, Yongli Hu, Junbin Gao, Jiapu Wang, Yanfeng Sun, Baocai Yin
In the realm of long document classification (LDC), previous research has predominantly focused on modeling unimodal texts, overlooking the potential of multi-modal documents incorporating images. To address this gap, we introduce an innovative approach for multi-modal long document classification based on the Hierarchical Prompt and Multi-modal Transformer (HPMT). The proposed HPMT method facilitates
-
Spatial reconstructed local attention Res2Net with F0 subband for fake speech detection Neural Netw. (IF 7.8) Pub Date : 2024-04-16 Cunhang Fan, Jun Xue, Jianhua Tao, Jiangyan Yi, Chenglong Wang, Chengshi Zheng, Zhao Lv
The rhythm of bonafide speech is often difficult to replicate, which causes that the fundamental frequency (F0) of synthetic speech is significantly different from that of real speech. It is expected that the F0 feature contains the discriminative information for the fake speech detection (FSD) task. In this paper, we propose a novel F0 subband for FSD. In addition, to effectively model the F0 subband
-
Contrastive Prototype-Guided Generation for Generalized Zero-Shot Learning Neural Netw. (IF 7.8) Pub Date : 2024-04-15 Yunyun Wang, Jian Mao, Chenguang Guo, Songcan Chen
Generalized zero-shot learning (GZSL) aims to recognize both seen and unseen classes, while only samples from seen classes are available for training. The mainstream methods mitigate the lack of unseen training data by simulating the visual unseen samples. However, the sample generator is actually learned with just seen-class samples, and semantic descriptions of unseen classes are just provided to
-
A proximal neurodynamic model for a system of non-linear inverse mixed variational inequalities Neural Netw. (IF 7.8) Pub Date : 2024-04-15 Anjali Upadhyay, Rahul Pandey
In this article, we introduce a system of non-linear inverse mixed variational inequalities (SNIMVIs). We propose a proximal neurodynamic model (PNDM) for solving SNIMVIs, leveraging proximal mappings. The uniqueness of the continuous solution for the PNDM is proved by assuming Lipschitz continuity. Moreover, we establish the global asymptotic stability of equilibrium points of the PNDM, contingent
-
A memristive all-inclusive hypernetwork for parallel analog deployment of full search space architectures Neural Netw. (IF 7.8) Pub Date : 2024-04-15 Bo Lyu, Yin Yang, Yuting Cao, Tuo Shi, Yiran Chen, Tingwen Huang, Shiping Wen
In recent years, there has been a significant advancement in memristor-based neural networks, positioning them as a pivotal processing-in-memory deployment architecture for a wide array of deep learning applications. Within this realm of progress, the emerging parallel analog memristive platforms are prominent for their ability to generate multiple feature maps in a single processing cycle. However
-
Score mismatching for generative modeling Neural Netw. (IF 7.8) Pub Date : 2024-04-15 Senmao Ye, Fei Liu
We propose a new score-based model with one-step sampling. Previously, score-based models were burdened with heavy computations due to iterative sampling. For substituting the iterative process, we train a standalone generator to compress all the time steps with the gradient backpropagated from the score network. In order to produce meaningful gradients for the generator, the score network is trained
-
Unsupervised Sentence Representation Learning with Frequency-induced Adversarial tuning and Incomplete sentence filtering Neural Netw. (IF 7.8) Pub Date : 2024-04-15 Bing Wang, Ximing Li, Zhiyao Yang, Yuanyuan Guan, Jiayin Li, Shengsheng Wang
Pre-trained Language Model (PLM) is nowadays the mainstay of Unsupervised Sentence Representation Learning (USRL). However, PLMs are sensitive to the frequency information of words from their pre-training corpora, resulting in anisotropic embedding space, where the embeddings of high-frequency words are clustered but those of low-frequency words disperse sparsely. This anisotropic phenomenon results
-
Weakly supervised temporal action localization with actionness-guided false positive suppression Neural Netw. (IF 7.8) Pub Date : 2024-04-15 Zhilin Li, Zilei Wang, Qinying Liu
Weakly supervised temporal action localization aims to locate the temporal boundaries of action instances in untrimmed videos using video-level labels and assign them the corresponding action category. Generally, it is solved by a pipeline called “localization-by-classification”, which finds the action instances by classifying video snippets. However, since this approach optimizes the video-level classification
-
Unsupervised Bidirectional Contrastive Reconstruction and Adaptive Fine-Grained Channel Attention Networks for image dehazing Neural Netw. (IF 7.8) Pub Date : 2024-04-14 Hang Sun, Yang Wen, Huijing Feng, Yuelin Zheng, Qi Mei, Dong Ren, Mei Yu
Recently, Unsupervised algorithms has achieved remarkable performance in image dehazing. However, the CycleGAN framework can lead to confusion in generator learning due to inconsistent data distributions, and the DisentGAN framework lacks effective constraints on generated images, resulting in the loss of image content details and color distortion. Moreover, Squeeze and Excitation channel attention
-
vEpiNet: A multimodal interictal epileptiform discharge detection method based on video and electroencephalogram data Neural Netw. (IF 7.8) Pub Date : 2024-04-14 Nan Lin, Weifang Gao, Lian Li, Junhui Chen, Zi Liang, Gonglin Yuan, Heyang Sun, Qing Liu, Jianhua Chen, Liri Jin, Yan Huang, Xiangqin Zhou, Shaobo Zhang, Peng Hu, Chaoyue Dai, Haibo He, Yisu Dong, Liying Cui, Qiang Lu
To enhance deep learning-based automated interictal epileptiform discharge (IED) detection, this study proposes a multimodal method, vEpiNet, that leverages video and electroencephalogram (EEG) data. Datasets comprise 24 931 IED (from 484 patients) and 166 094 non-IED 4-second video-EEG segments. The video data is processed by the proposed patient detection method, with frame difference and Simple
-
Mixing neural networks, continuation and symbolic computation to solve parametric systems of non linear equations Neural Netw. (IF 7.8) Pub Date : 2024-04-12 J.-P. Merlet
We consider a square non linear parametric equations system which is constituted of non differential equations in the unknowns that are the components of while is a set of parameters that play a role in the definition of the equations . We assume that is restricted to lie in a bounded region and we are interested in developing a solver for obtaining real solutions (a notion that is defined in the paper)
-
A neurocomputational model of decision and confidence in object recognition task Neural Netw. (IF 7.8) Pub Date : 2024-04-12 Setareh Sadat Roshan, Naser Sadeghnejad, Fatemeh Sharifizadeh, Reza Ebrahimpour
How does the brain process natural visual stimuli to make a decision? Imagine driving through fog. An object looms ahead. What do you do? This decision requires not only identifying the object but also choosing an action based on your decision confidence. In this circumstance, confidence is making a bridge between seeing and believing. Our study unveils how the brain processes visual information to
-
MTKSVCR: A novel multi-task multi-class support vector machine with safe acceleration rule Neural Netw. (IF 7.8) Pub Date : 2024-04-12 Xinying Pang, Chang Xu, Yitian Xu
Regularized multi-task learning (RMTL) has shown good performance in tackling multi-task binary problems. Although RMTL can be used to handle multi-class problems based on “one-versus-one” and “one-versus-rest” techniques, the information of the samples is not fully utilized and the class imbalance problem occurs. Motivated by the regularization technique in RMTL, we propose an original multi-task
-
Multiband task related components enhance rapid cognition decoding for both small and similar objects Neural Netw. (IF 7.8) Pub Date : 2024-04-10 Yusong Zhou, Banghua Yang, Changyong Wang
The cortically-coupled target recognition system based on rapid serial visual presentation (RSVP) has a wide range of applications in brain computer interface (BCI) fields such as medical and military. However, in the complex natural environment backgrounds, the identification of event-related potentials (ERP) of both small and similar objects that are quickly presented is a research challenge. Therefore
-
Non-local degradation modeling for spatially adaptive single image super-resolution Neural Netw. (IF 7.8) Pub Date : 2024-04-10 Qianyu Zhang, Bolun Zheng, Zongpeng Li, Yu Liu, Zunjie Zhu, Gregory Slabaugh, Shanxin Yuan
-
Adversarial infrared blocks: A multi-view black-box attack to thermal infrared detectors in physical world Neural Netw. (IF 7.8) Pub Date : 2024-04-09 Chengyin Hu, Weiwen Shi, Tingsong Jiang, Wen Yao, Ling Tian, Xiaoqian Chen, Jingzhi Zhou, Wen Li
Thermal infrared detectors have a vast array of potential applications in pedestrian detection and autonomous driving, and their safety performance is of great concern. Recent works use bulb plate, “QR” suit, and infrared patches as physical perturbations to perform white-box attacks on thermal infrared detectors, which are effective but not practical for real-world scenarios. Some researchers have
-
Expressive power of ReLU and step networks under floating-point operations Neural Netw. (IF 7.8) Pub Date : 2024-04-09 Yeachan Park, Geonho Hwang, Wonyeol Lee, Sejun Park
The study of the expressive power of neural networks has investigated the fundamental limits of neural networks. Most existing results assume real-valued inputs and parameters as well as exact operations during the evaluation of neural networks. However, neural networks are typically executed on computers that can only represent a tiny subset of the reals and apply inexact operations, i.e., most existing
-
Deep causal learning for pancreatic cancer segmentation in CT sequences Neural Netw. (IF 7.8) Pub Date : 2024-04-09 Chengkang Li, Yishen Mao, Shuyu Liang, Ji Li, Yuanyuan Wang, Yi Guo
Segmenting the irregular pancreas and inconspicuous tumor simultaneously is an essential but challenging step in diagnosing pancreatic cancer. Current deep-learning (DL) methods usually segment the pancreas or tumor independently using mixed image features, which are disrupted by surrounding complex and low-contrast background tissues. Here, we proposed a deep causal learning framework named CausegNet
-
Bridging flexible goal-directed cognition and consciousness: The Goal-Aligning Representation Internal Manipulation theory Neural Netw. (IF 7.8) Pub Date : 2024-04-08 Giovanni Granato, Gianluca Baldassarre
Goal-directed manipulation of internal representations is a key element of human flexible behaviour, while consciousness is commonly associated with higher-order cognition and human flexibility. Current perspectives have only partially linked these processes, thus preventing a clear understanding of how they jointly generate flexible cognition and behaviour. Moreover, these limitations prevent an effective
-
Physics-informed neural wavefields with Gabor basis functions Neural Netw. (IF 7.8) Pub Date : 2024-04-08 Tariq Alkhalifah, Xinquan Huang
Recently, Physics-Informed Neural Networks (PINNs) have gained significant attention for their versatile interpolation capabilities in solving partial differential equations (PDEs). Despite their potential, the training can be computationally demanding, especially for intricate functions like wavefields. This is primarily due to the neural-based (learned) basis functions, biased toward low frequencies
-
Connectional-style-guided contextual representation learning for brain disease diagnosis Neural Netw. (IF 7.8) Pub Date : 2024-04-07 Gongshu Wang, Ning Jiang, Yunxiao Ma, Duanduan Chen, Jinglong Wu, Guoqi Li, Dong Liang, Tianyi Yan
Structural magnetic resonance imaging (sMRI) has shown great clinical value and has been widely used in deep learning (DL) based computer-aided brain disease diagnosis. Previous DL-based approaches focused on local shapes and textures in brain sMRI that may be significant only within a particular domain. The learned representations are likely to contain spurious information and have poor generalization
-
Self-paced regularized adaptive multi-view unsupervised feature selection Neural Netw. (IF 7.8) Pub Date : 2024-04-06 Xuanhao Yang, Hangjun Che, Man-Fai Leung, Shiping Wen
Multi-view unsupervised feature selection (MUFS) is an efficient approach for dimensional reduction of heterogeneous data. However, existing MUFS approaches mostly assign the samples the same weight, thus the diversity of samples is not utilized efficiently. Additionally, due to the presence of various regularizations, the resulting MUFS problems are often non-convex, making it difficult to find the
-
Gossip-based distributed stochastic mirror descent for constrained optimization Neural Netw. (IF 7.8) Pub Date : 2024-04-05 Xianju Fang, Baoyong Zhang, Deming Yuan
This paper considers a distributed constrained optimization problem over a multi-agent network in the non-Euclidean sense. The gossip protocol is adopted to relieve the communication burden, which also adapts to the constantly changing topology of the network. Based on this idea, a gossip-based distributed stochastic mirror descent (GB-DSMD) algorithm is proposed to handle the problem under consideration
-
Investigation of out-of-distribution detection across various models and training methodologies Neural Netw. (IF 7.8) Pub Date : 2024-04-04 Byung Chun Kim, Byungro Kim, Yoonsuk Hyun
Machine learning-based algorithms demonstrate impressive performance across numerous fields; however, they continue to suffer from certain limitations. Even sophisticated and precise algorithms often make erroneous predictions when implemented with datasets having different distributions compared to the training set. Out-of-distribution (OOD) detection, which distinguishes data with different distributions
-
Bayesian tensor network structure search and its application to tensor completion Neural Netw. (IF 7.8) Pub Date : 2024-04-03 Junhua Zeng, Guoxu Zhou, Yuning Qiu, Chao Li, Qibin Zhao
Tensor network (TN) has demonstrated remarkable efficacy in the compact representation of high-order data. In contrast to the TN methods with pre-determined structures, the recently introduced tensor network structure search (TNSS) methods automatically learn a compact TN structure from the data, gaining increasing attention. Nonetheless, TNSS requires time-consuming manual adjustments of the penalty
-
Mutual Correlation Network for few-shot learning Neural Netw. (IF 7.8) Pub Date : 2024-04-03 Derong Chen, Feiyu Chen, Deqiang Ouyang, Jie Shao
Most metric-based Few-Shot Learning (FSL) methods focus on learning good embeddings of images. However, these methods either lack the ability to explore the cross-correlation (i.e., correlated information) between image pairs or explore limited consensus among the correlation map constrained by the limited receptive field of CNN. We propose a Mutual Correlation Network (MCNet) to explore global consensus
-
Structural deep multi-view clustering with integrated abstraction and detail Neural Netw. (IF 7.8) Pub Date : 2024-04-01 Bowei Chen, Sen Xu, Heyang Xu, Xuesheng Bian, Naixuan Guo, Xiufang Xu, Xiaopeng Hua, Tian Zhou
Deep multi-view clustering, which can obtain complementary information from different views, has received considerable attention in recent years. Although some efforts have been made and achieve decent performances, most of them overlook the structural information and are susceptible to poor quality views, which may seriously restrict the capacity for clustering. To this end, we propose tructural deep
-
A novel interactive deep cascade spectral graph convolutional network with multi-relational graphs for disease prediction Neural Netw. (IF 7.8) Pub Date : 2024-04-01 Sihui Li, Rui Zhang
Graph neural networks (GNNs) have recently grown in popularity for disease prediction. Existing GNN-based methods primarily build the graph topological structure around a single modality and combine it with other modalities to acquire feature representations of acquisitions. The complicated relationship in each modality, however, may not be well highlighted due to its specificity. Further, relatively
-
Uncertainty-aware prototypical learning for anomaly detection in medical images Neural Netw. (IF 7.8) Pub Date : 2024-03-30 Chao Huang, Yushu Shi, Bob Zhang, Ke Lyu
Anomalous object detection (AOD) in medical images aims to recognize the anomalous lesions, and is crucial for early clinical diagnosis of various cancers. However, it is a difficult task because of two reasons: (1) the diversity of the anomalous lesions and (2) the ambiguity of the boundary between anomalous lesions and their normal surroundings. Unlike existing single-modality AOD models based on
-
MV-SHIF: Multi-view symmetric hypothesis inference fusion network for emotion-cause pair extraction in documents Neural Netw. (IF 7.8) Pub Date : 2024-03-29 Cheng Yang, Hua Zhang, Bi Chen, Bo Jiang, Ye Wang
Emotion-cause pair extraction (ECPE) is a challenging task that aims to automatically identify pairs of emotions and their causes from documents. The difficulty of ECPE lies in distinguishing valid emotion-cause pairs from many irrelevant ones. Most previous methods have primarily focused on utilizing multi-task learning to extract semantic information solely from documents without explicitly encoding
-
Generalized latent multi-view clustering with tensorized bipartite graph Neural Netw. (IF 7.8) Pub Date : 2024-03-28 Dongping Zhang, Haonan Huang, Qibin Zhao, Guoxu Zhou
Tensor-based multi-view spectral clustering algorithms use tensors to model the structure of multi-dimensional data to take advantage of the complementary information and high-order correlations embedded in the graph, thus achieving impressive clustering performance. However, these algorithms use linear models to obtain consensus, which prevents the learned consensus from adequately representing the
-
Observer-based resilient dissipativity control for discrete-time memristor-based neural networks with unbounded or bounded time-varying delays Neural Netw. (IF 7.8) Pub Date : 2024-03-28 Kairong Tu, Yu Xue, Xian Zhang
This work focuses on the issue of observer-based resilient dissipativity control of discrete-time memristor-based neural networks (DTMBNNs) with unbounded or bounded time-varying delays. Firstly, the Luenberger observer is designed, and additionally based on the observed states, the observer-based resilient controller is proposed. An augmented system is presented by considering both the error system
-
A Dual Robust Graph Neural Network Against Graph Adversarial Attacks Neural Netw. (IF 7.8) Pub Date : 2024-03-28 Qian Tao, Jianpeng Liao, Enze Zhang, Lusi Li
Graph Neural Networks (GNNs) have gained widespread usage and achieved remarkable success in various real-world applications. Nevertheless, recent studies reveal the vulnerability of GNNs to graph adversarial attacks that fool them by modifying graph structure. This vulnerability undermines the robustness of GNNs and poses significant security and privacy risks across various applications. Hence, it
-
Frequency compensated diffusion model for real-scene dehazing Neural Netw. (IF 7.8) Pub Date : 2024-03-28 Jing Wang, Songtao Wu, Zhiqiang Yuan, Qiang Tong, Kuanhong Xu
Due to distribution shift, deep learning based methods for image dehazing suffer from performance degradation when applied to real-world hazy images. In this paper, this study considers a dehazing framework based on conditional diffusion models for improved generalization to real haze. First, our work finds that optimizing the training objective of diffusion models, i.e., Gaussian noise vectors, is
-
Medical image segmentation network based on multi-scale frequency domain filter Neural Netw. (IF 7.8) Pub Date : 2024-03-28 Yufeng Chen, Xiaoqian Zhang, Lifan Peng, Youdong He, Feng Sun, Huaijiang Sun
With the development of deep learning, medical image segmentation in computer-aided diagnosis has become a research hotspot. Recently, UNet and its variants have become the most powerful medical image segmentation methods. However, these methods suffer from (1) insufficient sensing field and insufficient depth; (2) computational nonlinearity and redundancy of channel features; and (3) ignoring the
-
Generalizability and robustness evaluation of attribute-based zero-shot learning Neural Netw. (IF 7.8) Pub Date : 2024-03-28 Luca Rossi, Maria Chiara Fiorentino, Adriano Mancini, Marina Paolanti, Riccardo Rosati, Primo Zingaretti
In the field of deep learning, large quantities of data are typically required to effectively train models. This challenge has given rise to techniques like zero-shot learning (ZSL), which trains models on a set of “seen” classes and evaluates them on a set of “unseen” classes. Although ZSL has shown considerable potential, particularly with the employment of generative methods, its generalizability
-
Face anti-spoofing with cross-stage relation enhancement and spoof material perception Neural Netw. (IF 7.8) Pub Date : 2024-03-27 Daiyuan Li, Guo Chen, Xixian Wu, Zitong Yu, Mingkui Tan
Face Anti-Spoofing (FAS) seeks to protect face recognition systems from spoofing attacks, which is applied extensively in scenarios such as access control, electronic payment, and security surveillance systems. Face anti-spoofing requires the integration of local details and global semantic information. Existing CNN-based methods rely on small stride or image patch-based feature extraction structures