International Journal of Neural Systems最新文献_第6页

Transformer-Based Approach Via Contrastive Learning for Zero-Shot Detection. 基于变压器对比学习的零弹检测方法。

IF 8 2区计算机科学

International Journal of Neural Systems Pub Date : 2023-07-01 DOI: 10.1142/S0129065723500351

Wei Liu, Hui Chen, Yongqiang Ma, Jianji Wang, Nanning Zheng

{"title":"Transformer-Based Approach Via Contrastive Learning for Zero-Shot Detection.","authors":"Wei Liu, Hui Chen, Yongqiang Ma, Jianji Wang, Nanning Zheng","doi":"10.1142/S0129065723500351","DOIUrl":"https://doi.org/10.1142/S0129065723500351","url":null,"abstract":"Zero-shot detection (ZSD) aims to locate and classify unseen objects in pictures or videos by semantic auxiliary information without additional training examples. Most of the existing ZSD methods are based on two-stage models, which achieve the detection of unseen classes by aligning object region proposals with semantic embeddings. However, these methods have several limitations, including poor region proposals for unseen classes, lack of consideration of semantic representations of unseen classes or their inter-class correlations, and domain bias towards seen classes, which can degrade overall performance. To address these issues, the Trans-ZSD framework is proposed, which is a transformer-based multi-scale contextual detection framework that explicitly exploits inter-class correlations between seen and unseen classes and optimizes feature distribution to learn discriminative features. Trans-ZSD is a single-stage approach that skips proposal generation and performs detection directly, allowing the encoding of long-term dependencies at multiple scales to learn contextual features while requiring fewer inductive biases. Trans-ZSD also introduces a foreground-background separation branch to alleviate the confusion of unseen classes and backgrounds, contrastive learning to learn inter-class uniqueness and reduce misclassification between similar classes, and explicit inter-class commonality learning to facilitate generalization between related classes. Trans-ZSD addresses the domain bias problem in end-to-end generalized zero-shot detection (GZSD) models by using balance loss to maximize response consistency between seen and unseen predictions, ensuring that the model does not bias towards seen classes. The Trans-ZSD framework is evaluated on the PASCAL VOC and MS COCO datasets, demonstrating significant improvements over existing ZSD models.","PeriodicalId":50305,"journal":{"name":"International Journal of Neural Systems","volume":null,"pages":null},"PeriodicalIF":8.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10188479","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Integrating Nearest Neighbors with Neural Network Models for Treatment Effect Estimation. 基于神经网络模型的最近邻集成治疗效果估计。

IF 8 2区计算机科学

International Journal of Neural Systems Pub Date : 2023-07-01 DOI: 10.1142/S0129065723500363

Niki Kiriakidou, Christos Diou

{"title":"Integrating Nearest Neighbors with Neural Network Models for Treatment Effect Estimation.","authors":"Niki Kiriakidou, Christos Diou","doi":"10.1142/S0129065723500363","DOIUrl":"https://doi.org/10.1142/S0129065723500363","url":null,"abstract":"Treatment effect estimation is of high-importance for both researchers and practitioners across many scientific and industrial domains. The abundance of observational data makes them increasingly used by researchers for the estimation of causal effects. However, these data suffer from several weaknesses, leading to inaccurate causal effect estimations, if not handled properly. Therefore, several machine learning techniques have been proposed, most of them focusing on leveraging the predictive power of neural network models to attain more precise estimation of causal effects. In this work, we propose a new methodology, named Nearest Neighboring Information for Causal Inference (NNCI), for integrating valuable nearest neighboring information on neural network-based models for estimating treatment effects. The proposed NNCI methodology is applied to some of the most well established neural network-based models for treatment effect estimation with the use of observational data. Numerical experiments and analysis provide empirical and statistical evidence that the integration of NNCI with state-of-the-art neural network models leads to considerably improved treatment effect estimations on a variety of well-known challenging benchmarks.","PeriodicalId":50305,"journal":{"name":"International Journal of Neural Systems","volume":null,"pages":null},"PeriodicalIF":8.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10206801","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

A Modified Long Short-Term Memory Cell. 一种改良的长短期记忆细胞。

IF 8 2区计算机科学

International Journal of Neural Systems Pub Date : 2023-07-01 DOI: 10.1142/S0129065723500399

Giannis Haralabopoulos, Gerasimos Razis, Ioannis Anagnostopoulos

{"title":"A Modified Long Short-Term Memory Cell.","authors":"Giannis Haralabopoulos, Gerasimos Razis, Ioannis Anagnostopoulos","doi":"10.1142/S0129065723500399","DOIUrl":"https://doi.org/10.1142/S0129065723500399","url":null,"abstract":"Machine Learning (ML), among other things, facilitates Text Classification, the task of assigning classes to textual items. Classification performance in ML has been significantly improved due to recent developments, including the rise of Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM), Gated Recurrent Units (GRUs), and Transformer Models. Internal memory states with dynamic temporal behavior can be found in these kinds of cells. This temporal behavior in the LSTM cell is stored in two different states: \"Current\" and \"Hidden\". In this work, we define a modification layer within the LSTM cell which allows us to perform additional state adjustments for either state, or even simultaneously alter both. We perform 17 state alterations. Out of these 17 single-state alteration experiments, 12 involve the Current state whereas five involve the Hidden one. These alterations are evaluated using seven datasets related to sentiment analysis, document classification, hate speech detection, and human-to-robot interaction. Our results showed that the highest performing alteration for Current and Hidden state can achieve an average F1 improvement of 0.5% and 0.3%, respectively. We also compare our modified cell performance to two Transformer models, where our modified LSTM cell is outperformed in classification metrics in 4/6 datasets, but improves upon the simple Transformer model and clearly has a better cost efficiency than both Transformer models.","PeriodicalId":50305,"journal":{"name":"International Journal of Neural Systems","volume":null,"pages":null},"PeriodicalIF":8.0,"publicationDate":"2023-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10206784","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Human Brain Dynamics and Coordination Reflect the Task Difficulty of Optical Image Relational Reasoning. 人脑动力学和协调性反映了光学图像关联推理的任务难度。

IF 8 2区计算机科学

International Journal of Neural Systems Pub Date : 2023-05-01 DOI: 10.1142/S0129065723500181

Wen-Chi Chou, Hsiao-Ching She, Tzyy-Ping Jung

{"title":"Human Brain Dynamics and Coordination Reflect the Task Difficulty of Optical Image Relational Reasoning.","authors":"Wen-Chi Chou, Hsiao-Ching She, Tzyy-Ping Jung","doi":"10.1142/S0129065723500181","DOIUrl":"https://doi.org/10.1142/S0129065723500181","url":null,"abstract":"Despite advances in neuroscience, the mechanisms by which human brain resolve optical image formation through relational reasoning remain unclear, particularly its relationships with task difficulty. Therefore, this study explores the underlying brain dynamics involved in optical image formation tasks at various difficulty levels, including those with a single convex lens and a single mirror. Compared to single convex lens relational reasoning with high task difficulty, the single mirror relational reasoning exhibited significantly higher response accuracy and shorter latency. As compared to single mirror tasks, single convex tasks exhibited greater frontal midline theta augmentation and right parietal alpha suppression during phase I and earlier phase II, and augmentation of frontal midline theta, right parietal-occipital alpha, and left mu alpha suppression during late phase II. Moreover, the frontal midline theta power in late phase II predicts the likelihood of solving single convex tasks the best, while the parietal alpha power in phase I is most predictive. In addition, frontal midline theta power exhibited stronger synchronization with right parietal alpha, right occipital alpha, and mu alpha power when solving single convex tasks than single mirror tasks. In summary, having stronger brain dynamics and coordination is vital for achieving optical image formation with greater difficulty.","PeriodicalId":50305,"journal":{"name":"International Journal of Neural Systems","volume":null,"pages":null},"PeriodicalIF":8.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9495574","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Method based on Evolutionary Algorithms and Channel Attention Mechanism to Enhance Cycle Generative Adversarial Network Performance for Image Translation. 基于进化算法和通道注意机制的图像翻译循环生成对抗网络性能提升方法。

IF 8 2区计算机科学

International Journal of Neural Systems Pub Date : 2023-05-01 DOI: 10.1142/S0129065723500260

Yu Xue, Yixia Zhang, Ferrante Neri

{"title":"A Method based on Evolutionary Algorithms and Channel Attention Mechanism to Enhance Cycle Generative Adversarial Network Performance for Image Translation.","authors":"Yu Xue, Yixia Zhang, Ferrante Neri","doi":"10.1142/S0129065723500260","DOIUrl":"https://doi.org/10.1142/S0129065723500260","url":null,"abstract":"A Generative Adversarial Network (GAN) can learn the relationship between two image domains and achieve unpaired image-to-image translation. One of the breakthroughs was Cycle-consistent Generative Adversarial Networks (CycleGAN), which is a popular method to transfer the content representations from the source domain to the target domain. Existing studies have gradually improved the performance of CycleGAN models by modifying the network structure or loss function of CycleGAN. However, these methods tend to suffer from training instability and the generators lack the ability to acquire the most discriminating features between the source and target domains, thus making the generated images of low fidelity and few texture details. To overcome these issues, this paper proposes a new method that combines Evolutionary Algorithms (EAs) and Attention Mechanisms to train GANs. Specifically, from an initial CycleGAN, binary vectors indicating the activation of the weights of the generators are progressively improved upon by means of an EA. At the end of this process, the best-performing configurations of generators can be retained for image generation. In addition, to address the issues of low fidelity and lack of texture details on generated images, we make use of the channel attention mechanism. The latter component allows the candidate generators to learn important features of real images and thus generate images with higher quality. The experiments demonstrate qualitatively and quantitatively that the proposed method, namely, Attention evolutionary GAN (AevoGAN) alleviates the training instability problems of CycleGAN training. In the test results, the proposed method can generate higher quality images and obtain better results than the CycleGAN training methods present in the literature, in terms of Inception Score (IS), Fréchet Inception Distance (FID) and Kernel Inception Distance (KID).","PeriodicalId":50305,"journal":{"name":"International Journal of Neural Systems","volume":null,"pages":null},"PeriodicalIF":8.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9496123","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Prediction Model Based on Gated Nonlinear Spiking Neural Systems. 基于门控非线性脉冲神经系统的预测模型。

IF 8 2区计算机科学

International Journal of Neural Systems Pub Date : 2023-05-01 DOI: 10.1142/S0129065723500296

Yujie Zhang, Qian Yang, Zhicai Liu, Hong Peng, Jun Wang

引用次数: 3

Using Virus Machines to Compute Pairing Functions. 使用病毒机计算配对函数。

IF 8 2区计算机科学

International Journal of Neural Systems Pub Date : 2023-05-01 DOI: 10.1142/S0129065723500235

Antonio Ramírez-de-Arellano, David Orellana-Martín, Mario J Pérez-Jiménez

引用次数: 1

Convolutional Neural Network Classification of Topographic Electroencephalographic Maps on Alcoholism. 酒精中毒脑电地形图的卷积神经网络分类。

IF 8 2区计算机科学

International Journal of Neural Systems Pub Date : 2023-05-01 DOI: 10.1142/S0129065723500259

Victor Borghi Gimenez, Suelen Lorenzato Dos Reis, Fábio M Simões de Souza

引用次数: 0

Hybrid Attention Network for Epileptic EEG Classification. 混合注意网络用于癫痫脑电分类。

IF 8 2区计算机科学

International Journal of Neural Systems Pub Date : 2023-05-01 DOI: 10.1142/S0129065723500314

Yanna Zhao, Jiatong He, Fenglin Zhu, Tiantian Xiao, Yongfeng Zhang, Ziwei Wang, Fangzhou Xu, Yi Niu

引用次数: 1

Facial Expression Recognition with Contrastive Learning and Uncertainty-Guided Relabeling. 面部表情识别的对比学习和不确定性引导下的再标记。

IF 8 2区计算机科学

International Journal of Neural Systems Pub Date : 2023-05-01 DOI: 10.1142/S0129065723500326

Yujie Yang, Lin Hu, Chen Zu, Qizheng Zhou, Xi Wu, Jiliu Zhou, Yan Wang

{"title":"Facial Expression Recognition with Contrastive Learning and Uncertainty-Guided Relabeling.","authors":"Yujie Yang, Lin Hu, Chen Zu, Qizheng Zhou, Xi Wu, Jiliu Zhou, Yan Wang","doi":"10.1142/S0129065723500326","DOIUrl":"https://doi.org/10.1142/S0129065723500326","url":null,"abstract":"Facial expression recognition (FER) plays a vital role in the field of human-computer interaction. To achieve automatic FER, various approaches based on deep learning (DL) have been presented. However, most of them lack for the extraction of discriminative expression semantic information and suffer from the problem of annotation ambiguity. In this paper, we propose an elaborately designed end-to-end recognition network with contrastive learning and uncertainty-guided relabeling, to recognize facial expressions efficiently and accurately, as well as to alleviate the impact of annotation ambiguity. Specifically, a supervised contrastive loss (SCL) is introduced to promote inter-class separability and intra-class compactness, thus helping the network extract fine-grained discriminative expression features. As for the annotation ambiguity problem, we present an uncertainty estimation-based relabeling module (UERM) to estimate the uncertainty of each sample and relabel the unreliable ones. In addition, to deal with the padding erosion problem, we embed an amending representation module (ARM) into the recognition network. Experimental results on three public benchmarks demonstrate that our proposed method facilitates the recognition performance remarkably with 90.91% on RAF-DB, 88.59% on FERPlus and 61.00% on AffectNet, outperforming current state-of-the-art (SOTA) FER methods. Code will be available at http//github.com/xiaohu-run/fer_supCon.","PeriodicalId":50305,"journal":{"name":"International Journal of Neural Systems","volume":null,"pages":null},"PeriodicalIF":8.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9537226","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1