2021 International Joint Conference on Neural Networks (IJCNN)最新文献_第3页

A Bayesian approach to Expert Gate Incremental Learning 专家门增量学习的贝叶斯方法

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9534204

Valerio Mieuli, Francesco Ponzio, Alessio Mascolini, E. Macii, E. Ficarra, S. D. Cataldo

{"title":"A Bayesian approach to Expert Gate Incremental Learning","authors":"Valerio Mieuli, Francesco Ponzio, Alessio Mascolini, E. Macii, E. Ficarra, S. D. Cataldo","doi":"10.1109/IJCNN52387.2021.9534204","DOIUrl":"https://doi.org/10.1109/IJCNN52387.2021.9534204","url":null,"abstract":"Incremental learning involves Machine Learning paradigms that dynamically adjust their previous knowledge whenever new training samples emerge. To address the problem of multi-task incremental learning without storing any samples of the previous tasks, the so-called Expert Gate paradigm was proposed, which consists of a Gate and a downstream network of task-specific CNNs, a.k.a. the Experts. The gate forwards the input to a certain expert, based on the decision made by a set of autoencoders. Unfortunately, as a CNN is intrinsically incapable of dealing with inputs of a class it was not specifically trained on, the activation of the wrong expert will invariably end into a classification error. To address this issue, we propose a probabilistic extension of the classic Expert Gate paradigm. Exploiting the prediction uncertainty estimations provided by Bayesian Convolutional Neural Networks (B-CNNs), the proposed paradigm is able to either reduce, or correct at a later stage, wrong decisions of the gate. The goodness of our approach is shown by experimental comparisons with state-of-the-art incremental learning methods.","PeriodicalId":396583,"journal":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126174495","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Context encoder self-supervised approaches for eye fundus analysis 眼底分析的上下文编码器自监督方法

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9533567

D. I. Morís, Álvaro S. Hervella, J. Rouco, J. Novo, M. Ortega

{"title":"Context encoder self-supervised approaches for eye fundus analysis","authors":"D. I. Morís, Álvaro S. Hervella, J. Rouco, J. Novo, M. Ortega","doi":"10.1109/IJCNN52387.2021.9533567","DOIUrl":"https://doi.org/10.1109/IJCNN52387.2021.9533567","url":null,"abstract":"The broad availability of medical images in current clinical practice provides a source of large image datasets. In order to use these datasets for training deep neural networks in detection and segmentation tools, it is necessary to provide pixel-wise annotations associated to each image. However, the image annotation is a tedious, time consuming and error prone process that requires the participation of experienced specialists. In this work, we propose different complementary context encoder self-supervised approaches to learn relevant characteristics for the restricted medical imaging domain of retinographies. In particular, we propose a patch-wise approach, inspired in the previous proposal of broad domain context encoders, and complementary fully convolutional approaches. These approaches take advantage of the restricted application domain to learn the relevant features of the eye fundus, situation that can be extrapolated to many medical imaging issues. Different representative experiments were conducted in order to evaluate the performance of the trained models, demonstrating the suitability of the proposed approaches in the understanding of the eye fundus characteristics. The proposed self-supervised models can serve as reference to support other domain-related issues through transfer or multi-task learning paradigms, like the detection and evaluation of the retinal structures or anomaly detections in the context of pathological analysis.","PeriodicalId":396583,"journal":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126186701","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Committee of NAS-based models 基于nas模型委员会

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9533446

B. S. Sette, L. C. Silva, Fernando R. Zagatt, L. N. S. Silva, D. Lucrédio, Helena de Medeiros Caseli, Diego Furtado Silva

引用次数: 0

Aspect-Based Sentiment Classification with Background Information and Syntactic Auxiliary Tasks 基于背景信息和句法辅助任务的面向方面情感分类

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9533506

Ming-Fan Li, Kaijie Zhou, Xuan Li, Jianping Shen

引用次数: 2

GAP-WF: Graph Attention Pooling Network for Fine-grained SSL/TLS Website Fingerprinting GAP-WF:用于细粒度SSL/TLS网站指纹识别的图注意力池网络

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9533543

Jie Lu, Gaopeng Gou, Majing Su, Dong Song, Chang Liu, Chen Yang, Yangyang Guan

{"title":"GAP-WF: Graph Attention Pooling Network for Fine-grained SSL/TLS Website Fingerprinting","authors":"Jie Lu, Gaopeng Gou, Majing Su, Dong Song, Chang Liu, Chen Yang, Yangyang Guan","doi":"10.1109/IJCNN52387.2021.9533543","DOIUrl":"https://doi.org/10.1109/IJCNN52387.2021.9533543","url":null,"abstract":"As an important part of network management, website fingerprinting has become one of the hottest topics in the field of encrypted traffic classification. Website fingerprinting aims to identify the specific webpages in encrypted traffic by observing patterns of traffic traces. Prior studies proposed several machine-learning-based methods using statistical features and deep-learning-based methods using packet length sequences. However, these works mainly focus on the website homepage fingerprinting. In fact, people are usually not limited to visiting the homepage. Compared with the homepage classification of websites, it is more difficult to identify different webpages within the same website due to the traffic traces are very similar. In this paper, we propose the Graph Attention Pooling Network for fine-grained website fingerprinting (GAP-WF). We introduce the trace graph to describe the contextual relationship between flows in webpage loading. Then we utilize the Graph Neural Networks to learn the intra-flow and inter-flow features. Considering different flows may have different importance, we utilize the graph attention mechanism to pay attention to key nodes. We collect four datasets covering three different granularity scenarios to evaluate our proposed method. Experimental results demonstrate that GAP-WF not only achieves the best performance of 99.86% in website homepage fingerprinting, but also outperforms other state-of-art methods in all fine-grained webpage fingerprinting scenarios. Moreover, GAP-WF can achieve better performance with fewer training samples.","PeriodicalId":396583,"journal":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125280375","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

Sentence Semantic Matching with Hierarchical CNN Based on Dimension-augmented Representation 基于维增表示的分层CNN句子语义匹配

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9533498

Rui Yu, Wenpeng Lu, Yifeng Li, Jiguo Yu, Guoqiang Zhang, Xu Zhang

{"title":"Sentence Semantic Matching with Hierarchical CNN Based on Dimension-augmented Representation","authors":"Rui Yu, Wenpeng Lu, Yifeng Li, Jiguo Yu, Guoqiang Zhang, Xu Zhang","doi":"10.1109/IJCNN52387.2021.9533498","DOIUrl":"https://doi.org/10.1109/IJCNN52387.2021.9533498","url":null,"abstract":"As a fundamental task in natural language processing, sentence semantic matching (SSM) is critical yet challenging due to difficulties in learning expressive sentence representation while capturing complex interactions between sentences. Recent work has shown the great potential of deep neural models in improving the performance of SSM task. However, existing work usually employs recurrent neural networks (RNNs) or 1D (one-dimensional) convolutional neural networks (CNNs) to learn sentence representation, leading to limited performance improvement. Benefiting from the multi-dimensional structure, 2D convolutional neural networks are expected to be more powerful to learn expressive sentence representation by capturing the implicit inter-sentence interactions and thus can further improve the performance of SSM. To this end, in this paper, we propose a novel sentence semantic matching model named Hierarchical CNN based on Dimension-augmented Representation (HiDR). In HiDR, first, bidirectional long short-term memory networks (LSTMs) are utilized to generate dimension-augmented representation for each of the input sentences; then, a hierarchical 2D CNN is devised to learn sentence representation while capturing the inter-sentence interactions, followed by a prediction layer based on sigmoid function to output the matching degree between sentences. To evaluate the performance of our proposed model, we conducted extensive experiments on two public real-world data sets. The empirical results show that HiDR has achieved remarkable results, which demonstrates either better or comparable performance w.r.t. BERT-based models.","PeriodicalId":396583,"journal":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125360585","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

A Transformer based Multi-task Model for Domain Classification, Intent Detection and Slot-Filling 基于Transformer的领域分类、意图检测和槽填充多任务模型

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9533525

Tulika Saha, N. Priya, S. Saha, P. Bhattacharyya

{"title":"A Transformer based Multi-task Model for Domain Classification, Intent Detection and Slot-Filling","authors":"Tulika Saha, N. Priya, S. Saha, P. Bhattacharyya","doi":"10.1109/IJCNN52387.2021.9533525","DOIUrl":"https://doi.org/10.1109/IJCNN52387.2021.9533525","url":null,"abstract":"With the ever increasing complexity of the user queries in a multi-domain based task-oriented dialogue system, it is imperative to facilitate robust Spoken Language Understanding (SLU) modules that perform multiple tasks in an unified way. In this paper, we present a novel multi-task approach for the joint modelling of three tasks together, namely, Domain Classification, Intent Detection and Slot-Filling. We hypothesize with the intuition that the cross dependencies of all these three tasks mutually help each other towards their representations and classifications which further simplify the SLU module in a multi-domain scenario. Towards this end, we propose a BERT language model based multi-task framework utilizing capsule networks and conditional random fields for addressing the classification and sequence labeling problems, respectively, for different tasks. Experimental results indicate that the proposed multi-task model outperformed several strong baselines and its single task counterparts on three benchmark datasets of different domains and attained state-of-the-art results on different tasks.","PeriodicalId":396583,"journal":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125518128","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Class-Decomposition and Augmentation for Imbalanced Data Sentiment Analysis 非平衡数据情感分析的类分解与增强

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9533603

C. Moreno-García, Chrisina Jayne, Eyad Elyan

引用次数: 2

Sequence Squeezing: A Defense Method Against Adversarial Examples for API Call-Based RNN Variants 序列压缩:一种针对基于API调用的RNN变体的对抗示例的防御方法

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9534432

Ishai Rosenberg, A. Shabtai, Y. Elovici, L. Rokach

{"title":"Sequence Squeezing: A Defense Method Against Adversarial Examples for API Call-Based RNN Variants","authors":"Ishai Rosenberg, A. Shabtai, Y. Elovici, L. Rokach","doi":"10.1109/IJCNN52387.2021.9534432","DOIUrl":"https://doi.org/10.1109/IJCNN52387.2021.9534432","url":null,"abstract":"Adversarial examples are known to mislead deep learning models so that the models will classify them incorrectly, even in domains where such models have achieved state-of-the-art performance. Until recently, research on both adversarial attack and defense methods focused on computer vision, primarily using convolutional neural networks (CNNs). In recent years, adversarial example generation methods for recurrent neural networks (RNNs) have been published, demonstrating that RNN classifiers are also vulnerable to such attacks. In this paper, we present a novel defense method, referred to as sequence squeezing, aimed at making RNN variant (e.g., LSTM) classifiers more robust against such attacks. Our method differs from existing defense methods, which were designed only for non-sequence based models. We also implement three additional defense methods inspired by recently published CNN defense methods as baselines for our method. Using sequence squeezing, we were able to decrease the effectiveness of such adversarial attacks from 99.9% to 15%, outperforming all of the baseline defense methods.","PeriodicalId":396583,"journal":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","volume":"123 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115041289","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 6

Graph Convolutional Neural Networks-based 3D Hand Pose Estimation over Point Clouds 基于卷积神经网络的点云三维手部姿态估计

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9533565

John Alejandro Castro-Vargas, P. Martinez-Gonzalez, Sergiu Oprea, Alberto Garcia-Garcia, S. Orts-Escolano, J. Garcia-Rodriguez

{"title":"Graph Convolutional Neural Networks-based 3D Hand Pose Estimation over Point Clouds","authors":"John Alejandro Castro-Vargas, P. Martinez-Gonzalez, Sergiu Oprea, Alberto Garcia-Garcia, S. Orts-Escolano, J. Garcia-Rodriguez","doi":"10.1109/IJCNN52387.2021.9533565","DOIUrl":"https://doi.org/10.1109/IJCNN52387.2021.9533565","url":null,"abstract":"In recent years we can find a multitude of approaches that aim to return the 3D pose of the hands. Most of them try to estimate the pose from RGB images or even include some geometrical information via depth maps. Furthermore, some proposals have shown promising results using point clouds as input data. However, the sparse nature of this type of data is often one of its drawbacks. To tackle this sparsity, different strategies have been brought to the table such as voxelizing or sorting the input data to impose a structure to the input domain. In this paper, we address this problem by means of a graph structure. This process implies that we should accommodate the point cloud onto a graph representation that connects its points. We connect each point to its neighborhood, a method that has been successfully used in similar proposals and whose clustering effect enables us to emulate an effect similar to kernels in image convolutions. The proposed architecture uses both graph and 2D convolutions. The first one aims to extract local features and build a feature map, from which the 2D convolutions will extract a second level of features used to estimate the pose. This proposal shows initial results to return a 3D pose of the hand from depth maps, which are projected on point clouds and redefined as graphs. Although the results diverge from other more established methods in the state of the art, it presents a proof of concept by which to address this problem without losing spatial information.","PeriodicalId":396583,"journal":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115195220","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0