International Conference on Neural Information Processing最新文献_第3页

MVNet: Memory Assistance and Vocal Reinforcement Network for Speech Enhancement 语音增强的记忆辅助和声音强化网络

International Conference on Neural Information Processing Pub Date : 2022-09-15 DOI: 10.48550/arXiv.2209.07302

Jianrong Wang, Xiaomin Li, Xuewei Li, Mei Yu, Qiang Fang, Li Liu

引用次数: 0

Cooperation and Competition: Flocking with Evolutionary Multi-Agent Reinforcement Learning 合作与竞争:基于进化多智能体强化学习的群集

International Conference on Neural Information Processing Pub Date : 2022-09-10 DOI: 10.48550/arXiv.2209.04696

Yunxiao Guo, Xinjia Xie, Runhao Zhao, Chenglan Zhu, Jiangting Yin, Han Long

引用次数: 1

ADTR: Anomaly Detection Transformer with Feature Reconstruction ADTR:带有特征重构的异常检测变压器

International Conference on Neural Information Processing Pub Date : 2022-09-05 DOI: 10.48550/arXiv.2209.01816

Zhiyuan You, Kai Yang, Wenhan Luo, Lei Cui, Xinyi Le, Yu Zheng

{"title":"ADTR: Anomaly Detection Transformer with Feature Reconstruction","authors":"Zhiyuan You, Kai Yang, Wenhan Luo, Lei Cui, Xinyi Le, Yu Zheng","doi":"10.48550/arXiv.2209.01816","DOIUrl":"https://doi.org/10.48550/arXiv.2209.01816","url":null,"abstract":"Anomaly detection with only prior knowledge from normal samples attracts more attention because of the lack of anomaly samples. Existing CNN-based pixel reconstruction approaches suffer from two concerns. First, the reconstruction source and target are raw pixel values that contain indistinguishable semantic information. Second, CNN tends to reconstruct both normal samples and anomalies well, making them still hard to distinguish. In this paper, we propose Anomaly Detection TRansformer (ADTR) to apply a transformer to reconstruct pre-trained features. The pre-trained features contain distinguishable semantic information. Also, the adoption of transformer limits to reconstruct anomalies well such that anomalies could be detected easily once the reconstruction fails. Moreover, we propose novel loss functions to make our approach compatible with the normal-sample-only case and the anomaly-available case with both image-level and pixel-level labeled anomalies. The performance could be further improved by adding simple synthetic or external irrelevant anomalies. Extensive experiments are conducted on anomaly detection datasets including MVTec-AD and CIFAR-10. Our method achieves superior performance compared with all baselines.","PeriodicalId":281152,"journal":{"name":"International Conference on Neural Information Processing","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116520690","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: 8

An Unsupervised Short- and Long-Term Mask Representation for Multivariate Time Series Anomaly Detection 多变量时间序列异常检测的无监督长短期掩码表示

International Conference on Neural Information Processing Pub Date : 2022-08-19 DOI: 10.48550/arXiv.2208.09240

Qiucheng Miao, Chuanfu Xu, Jun Zhan, Dong Zhu, Cheng-Feng Wu

{"title":"An Unsupervised Short- and Long-Term Mask Representation for Multivariate Time Series Anomaly Detection","authors":"Qiucheng Miao, Chuanfu Xu, Jun Zhan, Dong Zhu, Cheng-Feng Wu","doi":"10.48550/arXiv.2208.09240","DOIUrl":"https://doi.org/10.48550/arXiv.2208.09240","url":null,"abstract":"Anomaly detection of multivariate time series is meaningful for system behavior monitoring. This paper proposes an anomaly detection method based on unsupervised Short- and Long-term Mask Representation learning (SLMR). The main idea is to extract short-term local dependency patterns and long-term global trend patterns of the multivariate time series by using multi-scale residual dilated convolution and Gated Recurrent Unit(GRU) respectively. Furthermore, our approach can comprehend temporal contexts and feature correlations by combining spatial-temporal masked self-supervised representation learning and sequence split. It considers the importance of features is different, and we introduce the attention mechanism to adjust the contribution of each feature. Finally, a forecasting-based model and a reconstruction-based model are integrated to focus on single timestamp prediction and latent representation of time series. Experiments show that the performance of our method outperforms other state-of-the-art models on three real-world datasets. Further analysis shows that our method is good at interpretability.","PeriodicalId":281152,"journal":{"name":"International Conference on Neural Information Processing","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132482398","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

Towards Better Dermoscopic Image Feature Representation Learning for Melanoma Classification 面向黑色素瘤分类的更好的皮肤镜图像特征表示学习

International Conference on Neural Information Processing Pub Date : 2022-07-15 DOI: 10.1007/978-3-030-92273-3_45

Chen-Ping Yu, Mingkang Tang, Sheng Yang, Mingqing Wang, Zhe Xu, Jiangpeng Yan, Hanmo Chen, Yu Yang, X. Zeng, Xiu Li

引用次数: 0

Schizophrenia Detection Based on EEG Using Recurrent Auto-encoder Framework 基于循环自编码器框架的脑电精神分裂症检测

International Conference on Neural Information Processing Pub Date : 2022-07-09 DOI: 10.1007/978-3-031-30108-7_6

Yihan Wu, Min Xia, Xiuzhu Wang, Yangsong Zhang

引用次数: 4

StatMix: Data augmentation method that relies on image statistics in federated learning StatMix:在联邦学习中依赖图像统计的数据增强方法

International Conference on Neural Information Processing Pub Date : 2022-07-08 DOI: 10.48550/arXiv.2207.04103

D. Lewy, Jacek Ma'ndziuk, M. Ganzha, M. Paprzycki

引用次数: 2

Selectively increasing the diversity of GAN-generated samples 选择性地增加gan生成样品的多样性

International Conference on Neural Information Processing Pub Date : 2022-07-04 DOI: 10.48550/arXiv.2207.01561

Jan Dubi'nski, K. Deja, S. Wenzel, Przemyslaw Rokita, T. Trzci'nski

{"title":"Selectively increasing the diversity of GAN-generated samples","authors":"Jan Dubi'nski, K. Deja, S. Wenzel, Przemyslaw Rokita, T. Trzci'nski","doi":"10.48550/arXiv.2207.01561","DOIUrl":"https://doi.org/10.48550/arXiv.2207.01561","url":null,"abstract":"Generative Adversarial Networks (GANs) are powerful models able to synthesize data samples closely resembling the distribution of real data, yet the diversity of those generated samples is limited due to the so-called mode collapse phenomenon observed in GANs. Especially prone to mode collapse are conditional GANs, which tend to ignore the input noise vector and focus on the conditional information. Recent methods proposed to mitigate this limitation increase the diversity of generated samples, yet they reduce the performance of the models when similarity of samples is required. To address this shortcoming, we propose a novel method to selectively increase the diversity of GAN-generated samples. By adding a simple, yet effective regularization to the training loss function we encourage the generator to discover new data modes for inputs related to diverse outputs while generating consistent samples for the remaining ones. More precisely, we maximise the ratio of distances between generated images and input latent vectors scaling the effect according to the diversity of samples for a given conditional input. We show the superiority of our method in a synthetic benchmark as well as a real-life scenario of simulating data from the Zero Degree Calorimeter of ALICE experiment in LHC, CERN.","PeriodicalId":281152,"journal":{"name":"International Conference on Neural Information Processing","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126422247","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

Progressive Latent Replay for efficient Generative Rehearsal 用于高效生成式排练的渐进潜重放

International Conference on Neural Information Processing Pub Date : 2022-07-04 DOI: 10.48550/arXiv.2207.01562

Stanislaw Pawlak, Filip Szatkowski, Michał Bortkiewicz, Jan Dubi'nski, T. Trzci'nski

引用次数: 0

Anomaly detection in surveillance videos using transformer based attention model 基于变压器注意力模型的监控视频异常检测

International Conference on Neural Information Processing Pub Date : 2022-06-03 DOI: 10.48550/arXiv.2206.01524

Kapil Deshpande, N. Punn, S. K. Sonbhadra, Sonali Agarwal

{"title":"Anomaly detection in surveillance videos using transformer based attention model","authors":"Kapil Deshpande, N. Punn, S. K. Sonbhadra, Sonali Agarwal","doi":"10.48550/arXiv.2206.01524","DOIUrl":"https://doi.org/10.48550/arXiv.2206.01524","url":null,"abstract":"Surveillance footage can catch a wide range of realistic anomalies. This research suggests using a weakly supervised strategy to avoid annotating anomalous segments in training videos, which is time consuming. In this approach only video level labels are used to obtain frame level anomaly scores. Weakly supervised video anomaly detection (WSVAD) suffers from the wrong identification of abnormal and normal instances during the training process. Therefore it is important to extract better quality features from the available videos. WIth this motivation, the present paper uses better quality transformer-based features named Videoswin Features followed by the attention layer based on dilated convolution and self attention to capture long and short range dependencies in temporal domain. This gives us a better understanding of available videos. The proposed framework is validated on real-world dataset i.e. ShanghaiTech Campus dataset which results in competitive performance than current state-of-the-art methods. The model and the code are available at https://github.com/kapildeshpande/Anomaly-Detection-in-Surveillance-Videos","PeriodicalId":281152,"journal":{"name":"International Conference on Neural Information Processing","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129419327","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