2021 International Joint Conference on Neural Networks (IJCNN)最新文献_第4页

Soft Upper-bound Minimal Complexity LP SVMs 软上限最小复杂度LP支持向量机

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9533540

S. Abe

引用次数: 1

Coresets Application in Channel Pruning for Fast Neural Network Slimming 核集在快速神经网络瘦身通道剪枝中的应用

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9533343

Wenfeng Yin, Gang Dong, Yaqian Zhao, Rengang Li

{"title":"Coresets Application in Channel Pruning for Fast Neural Network Slimming","authors":"Wenfeng Yin, Gang Dong, Yaqian Zhao, Rengang Li","doi":"10.1109/IJCNN52387.2021.9533343","DOIUrl":"https://doi.org/10.1109/IJCNN52387.2021.9533343","url":null,"abstract":"Pruning reduces neural networks' parameters and accelerates inferences, enabling deep learning in resource-limited scenarios. Existing saliency-based pruning methods apply characteristics of feature maps or weights to judge the importance of neurons or structures, where weights' characteristics based methods are data-independent and robust for future input data. This paper proposes a coreset based pruning method for the data-independent structured compression, aiming to improve the construction efficiency of pruning. The first step of our method is to prune channels, according to the channel coreset merged from multi-rounds coresets constructions. Our method adjusts the importance function utilized in the random probability sampling during coresets construction procedures to achieve data-independent channel selections. The second step is recovering the precision of compressed networks through solving the compressed weights reconstruction by linear least squares. Our method is also generalized to implementations on multi-branch networks such as SqueezeNet and MobileNet-v2. In tests on classification networks like ResNet, it is observed that our method performs fast and achieves an accuracy decline as small as 0.99% when multiple layers are pruned without finetuning. As shown in evaluations on object detection networks, our method acquires the least decline in mAP indicator compared to comparison schemes, due to the advantage of data-independent channel selections of our method in preserving precision.","PeriodicalId":396583,"journal":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","volume":"146 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":"116447672","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

DS-TAGCN: A Dual-Stream Topology Attentive GCN for Node Classification in Dynamic Graphs DS-TAGCN:用于动态图中节点分类的双流拓扑关注GCN

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9533699

Jinteng Ruan, Hao-peng Chen, Ziming Wang, Shuyu Chen

{"title":"DS-TAGCN: A Dual-Stream Topology Attentive GCN for Node Classification in Dynamic Graphs","authors":"Jinteng Ruan, Hao-peng Chen, Ziming Wang, Shuyu Chen","doi":"10.1109/IJCNN52387.2021.9533699","DOIUrl":"https://doi.org/10.1109/IJCNN52387.2021.9533699","url":null,"abstract":"With the rapid growth of information, large amounts of graph-structured data have been generated. As an important task in graph-structured data research, node classification, which aims to classify nodes into different categories, has attracted a lot of attention from researchers in recent years. Real-life graphs are often dynamic whose graph topology and node attributes are constantly evolving. However, most of the studies focus on static graphs which can not capture the evolution of dynamic graphs. Node classification in dynamic graphs mainly has the following two challenges. First, it is difficult to effectively integrate modeling spatial and temporal features. Second, the evolution of dynamic graphs is located not only in node attributes but also in the graph topology. It is hard to learn the evolution of both aspects in the meantime. Besides, existing methods focus only on topological relations connected by explicit edges, while ignoring implicit topological relations that act in non-edge form. Implicit topological relations can help aggregate neighborhood features and further refine the modeling of node evolution patterns. To address these challenges and problems, we propose DS-TAGCN, a dual-stream topology attentive GCN for dynamic graph node classification. DS- TAGCN learns spatial-temporal features simultaneously by using a combination of GCN and LSTM. A dual-stream framework is designed to focus on the evolution of node attributes and graph topology, respectively. To mine the implicit topology, we propose TAGCN instead of GCN to model the implicit topological relations. Additionally, we incorporate a hierarchical attention mechanism in the network to automatically model the importance of different dimensional features. Extensive experiments demonstrate the effectiveness of DS-TAGCN.","PeriodicalId":396583,"journal":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","volume":"82 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":"122305240","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

Online Virtual Training in Soft Actor-Critic for Autonomous Driving 自动驾驶软演员评价的在线虚拟训练

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9533791

Maryam Savari, Y. Choe

{"title":"Online Virtual Training in Soft Actor-Critic for Autonomous Driving","authors":"Maryam Savari, Y. Choe","doi":"10.1109/IJCNN52387.2021.9533791","DOIUrl":"https://doi.org/10.1109/IJCNN52387.2021.9533791","url":null,"abstract":"Deep Reinforcement Learning (RL) algorithms are widely being used in autonomous driving due to their ability to cope with unseen environments. However, in a complex domain like autonomous driving, these algorithms need to explore the environment enough to be able to converge. Therefore, these algorithms are faced with the problem of long training times and large amounts of data. In addition, using deep RL algorithms in areas that safety is an important factor such as autonomous driving can lead to a safety issue since we cannot leave the car driving in the street unattended. In this research, we tested two methods for the purpose of reducing the training time. First, we pre-trained Soft Actor-Critic (SAC) with Learning from Demonstrations (LfD) to find out if pre-training can reduce the training time of the SAC algorithm. Then, an online end-to-end combination method of SAC, LfD, and Learning from Interventions (LfI) is proposed to train an agent (dubbed Online Virtual Training). Both scenarios were implemented and tested in an inverted-pendulum task in OpenAI gym and autonomous driving in the Carla simulator. The results showed a dramatic reduction in the training time and a significant increase in gaining rewards for Online LfD (33%) and Online Virtual training (36 %) as compare to the baseline SAC. The proposed approach is expected to be effective in daily commute scenarios for autonomous driving.","PeriodicalId":396583,"journal":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","volume":"32 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":"122312745","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

Driving Maneuver Detection using Features of Driver's attention and Face Shift through Deeping Learning 基于深度学习的驾驶员注意力和面部转移特征的驾驶机动检测

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9534110

Song Wang, Y. Murphey

引用次数: 1

Learning to Binarize Convolutional Neural Networks with Adaptive Neural Encoder 用自适应神经编码器学习卷积神经网络二值化

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9533480

Shuai Zhang, Fangyuan Ge, Rui Ding, Haijun Liu, Xichuan Zhou

{"title":"Learning to Binarize Convolutional Neural Networks with Adaptive Neural Encoder","authors":"Shuai Zhang, Fangyuan Ge, Rui Ding, Haijun Liu, Xichuan Zhou","doi":"10.1109/IJCNN52387.2021.9533480","DOIUrl":"https://doi.org/10.1109/IJCNN52387.2021.9533480","url":null,"abstract":"The high computational complexity and memory consumption of the deep Convolutional Neural Networks (CNNs) restrict their deployability in resource-limited embedded devices. To address this challenge, emerging solutions are proposed for neural network quantization and compression. Among them, Binary Neural Networks (BNNs) show their potential in reducing computational and memory complexity; however, they suffer from considerable performance degradation. One of the major causes is their non-differentiable discrete quantization implemented using a fixed sign function, which leads to output distribution distortion. In this paper, instead of using the fixed and naive sign function, we propose a novel adaptive Neural Encoder (NE), which learns to quantize the full-precision weights as binary values. Inspired by the research of neural network distillation, a distribution loss is introduced as a regularizer to minimize the Kullback-Leibler divergence between the outputs of the full-precision model and the encoded binary model. With an end-to-end backpropagation training process, the adaptive neural encoder, along with the binary convolutional neural network, could reach convergence iteratively. Comprehensive experiments with different network structures and datasets show that the proposed method can improve the performance of the baselines and also outperform many state-of-the-art approaches. The source code of the proposed method is publicly available at https://github.com/CQUlearningsystemgroup/LearningToBinarize.","PeriodicalId":396583,"journal":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","volume":"102 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":"122465624","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: 3

CMVCG: Non-autoregressive Conditional Masked Live Video Comments Generation Model CMVCG:非自回归条件屏蔽直播视频评论生成模型

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9533460

Zehua Zeng, Chenyang Tu, Neng Gao, Cong Xue, Cunqing Ma, Yiwei Shan

{"title":"CMVCG: Non-autoregressive Conditional Masked Live Video Comments Generation Model","authors":"Zehua Zeng, Chenyang Tu, Neng Gao, Cong Xue, Cunqing Ma, Yiwei Shan","doi":"10.1109/IJCNN52387.2021.9533460","DOIUrl":"https://doi.org/10.1109/IJCNN52387.2021.9533460","url":null,"abstract":"The blooming of live comment videos leads to the need of automatic live video comment generating task. Previous works focus on autoregressive live video comments generation and can only generate comments by giving the first word of the target comment. However, in some scenes, users need to generate comments by their given prompt keywords, which can't be solved by the traditional live video comment generation methods. In this paper, we propose a Transformer based non-autoregressive conditional masked live video comments generation model called CMVCG model. Our model considers not only the visual and textual context of the comments, but also time and color information. To predict the position of the given prompt keywords, we also introduce a keywords position predicting module. By leveraging the conditional masked language model, our model achieves non-autoregressive live video comment generation. Furthermore, we collect and introduce a large-scale real-world live video comment dataset called Bili-22 dataset. We evaluate our model in two live comment datasets and the experiment results present that our model outperforms the state-of-the-art models in most of the metrics.","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":"122625952","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

An Intrusion Detection System based on PSO-GWO Hybrid Optimized Support Vector Machine 基于PSO-GWO混合优化支持向量机的入侵检测系统

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9534325

Kexin Li, Yong Zhang, Shuai Wang

引用次数: 1

A Novel and High-Accuracy Rumor Detection Approach using Kernel Subtree and Deep Learning Networks 一种基于核子树和深度学习网络的高精度谣言检测方法

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9534311

Ziyu Wei, Xi Xiao, Guangwu Hu, Bin Zhang, Qing Li, Shutao Xia

{"title":"A Novel and High-Accuracy Rumor Detection Approach using Kernel Subtree and Deep Learning Networks","authors":"Ziyu Wei, Xi Xiao, Guangwu Hu, Bin Zhang, Qing Li, Shutao Xia","doi":"10.1109/IJCNN52387.2021.9534311","DOIUrl":"https://doi.org/10.1109/IJCNN52387.2021.9534311","url":null,"abstract":"Rumor detection is a task of identifying information that spread among people whose truth value is false or unverified, and it has been a great challenge due to the rapid development of social media. The traditional machine learning based detection methods can make full use of informative features but cannot extract high-level representations. Other methods involved deep learning neural networks exploit propagation structural information to achieve high accuracy, for example, Bi-Directional Graph Convolution Networks(BiGCN) achieved the best performance on rumor detection by operating on bottom-up and top-down structures. However, those deep learning methods ignore other useful features like content-based features. In this paper, we not only make full use of three aspects of features based on a new concept: kernel subtree, which focus more on informative features of influential nodes of an event, but also propose a new model, which consists of Separation Convolution blocks, Long Short Term Memory(LSTM) and Squeeze and Excitation Networks(SENet), to make comprehensive use of features extracted on the basis of kernel subtree. First, we utilize Separation Convolutions to learn more local information with different kernel size, then LSTM can learn high-level interactions among features and find more global information. After that, SENet applies attention mechanism to put more weights on informative channels of feature maps. Meanwhile, on test set, Gradient Boosting Decision Tree(GBDT) is used to assist our model with few events. The experiments on the PHEME dataset show that our approach can identify rumors with accuracy 95% which outperforms BiGCN by 10% at least.","PeriodicalId":396583,"journal":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","volume":"124 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":"123004044","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

Do We Really Reduce Bias for Scene Graph Generation? 我们真的能减少场景图生成的偏差吗?

2021 International Joint Conference on Neural Networks (IJCNN) Pub Date : 2021-07-18 DOI: 10.1109/IJCNN52387.2021.9533447

Haiyan Gao, Xin Tian, Yi Ji, Ying Li, Chunping Liu

{"title":"Do We Really Reduce Bias for Scene Graph Generation?","authors":"Haiyan Gao, Xin Tian, Yi Ji, Ying Li, Chunping Liu","doi":"10.1109/IJCNN52387.2021.9533447","DOIUrl":"https://doi.org/10.1109/IJCNN52387.2021.9533447","url":null,"abstract":"For a given image, the corresponding scene graph is a kind of structural expression which benefits to high-level tasks. To generate a meaningful and useful one, the existing models pay more attention on reducing the bias from long-tail distribution of dataset. However, they overlook the unimodal bias and evaluation bias from models themselves. In this paper, we construct an unbiased solution called Balanced Label and Vision for Multilabel Classification (BLVMC). BLVMC consists of two modules, label-vision grounding module (LVGM) and no graph constraint (NGC). Specially, the LVGM aims to be in equilibrium for label and vision by introducing visual information into label branch. This module reduces unimodal bias from previous models and makes them more stable. The NGC views the Scene Graph Generation (SGG) as a multilabel classification task instead of multiclass classification. Besides, the NGC uses the corresponding NGC mR@K to evaluate models. This module allows each subject-object pair to retain multi-predicates, which relieves evaluation bias. The quantitative and qualitative experiments on Visual Genome (VG) dataset demonstrate the proposed BLVMC effectively eliminates the above two biases and outperforms previous state-of-the-art models.","PeriodicalId":396583,"journal":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","volume":"67 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":"114300469","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