2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)最新文献_第2页

Gaussian Approximations of SDES in Metropolis-Adjusted Langevin Algorithms Metropolis-Adjusted Langevin算法中SDES的高斯逼近

2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596301

S. Särkkä, Christos Merkatas, T. Karvonen

引用次数: 0

SiamNet: Siamese CNN Based Similarity Model for Adversarially Generated Environmental Sounds SiamNet:基于Siamese CNN的相似度模型，用于对抗生成的环境声音

2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596435

Aswathy Madhu, S. Kumaraswamy

{"title":"SiamNet: Siamese CNN Based Similarity Model for Adversarially Generated Environmental Sounds","authors":"Aswathy Madhu, S. Kumaraswamy","doi":"10.1109/mlsp52302.2021.9596435","DOIUrl":"https://doi.org/10.1109/mlsp52302.2021.9596435","url":null,"abstract":"Recently, Generative Adversarial Networks (GANs) are being used extensively in machine learning applications for synthetic generation of image and audio samples. However efficient methods for the evaluation of the quality of GAN generated samples are not available yet. Moreover, most of the existing evaluation metrics are developed exclusively for images which may not work well with other types of data such as audio. Evaluation metrics developed specifically for audio are rare and hence the generation of perceptually acceptable audio using GAN is difficult. In this work, we address this problem. We propose Siamese CNN which simultaneously learns feature representation and similarity measure to evaluate the quality of synthetic audio generated by GAN. The proposed method estimates the perceptual proximity between the original and generated samples. Our similarity model is trained on two standard datasets of environmental sounds. The pre-trained model is evaluated on the environmental sounds generated using GAN. The predicted mean similarity score of the SiamNet are highly correlated with human ratings at the class level. This indicates that our model successfully captures the perceptual similarity between the generated and original audio samples.","PeriodicalId":156116,"journal":{"name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125879747","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

An Empirical Comparison of Joint-Training and Pre-Training for Domain-Agnostic Semi-Supervised Learning Via Energy-Based Models 基于能量模型的领域不可知半监督学习联合训练与预训练的实证比较

2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596559

Yunfu Song, Huahuan Zheng, Zhijian Ou

{"title":"An Empirical Comparison of Joint-Training and Pre-Training for Domain-Agnostic Semi-Supervised Learning Via Energy-Based Models","authors":"Yunfu Song, Huahuan Zheng, Zhijian Ou","doi":"10.1109/mlsp52302.2021.9596559","DOIUrl":"https://doi.org/10.1109/mlsp52302.2021.9596559","url":null,"abstract":"Some semi-supervised learning (SSL) methods heavily rely on domain-specific data augmentations. Recently, semi-supervised learning (SSL) via energy-based models (EBMs) has been studied and is attractive from the perspective of being domain-agnostic, since it inherently does not require data augmentations. There exist two different methods for EBM based SSL - joint-training and pre-training. Joint-training estimates the joint distribution of observations and labels, while pre-training is taken over observations only and followed by fine-tuning. Both joint-training and pre-training are previously known in the literature, but it is unclear which one is better when evaluated in a common experimental setup. To the best of our knowledge, this paper is the first to systematically compare joint-training and pre-training for EBM-based for SSL, by conducting a suite of experiments across a variety of domains such as image classification and natural language labeling. It is found that joint-training EBMs outperform pre-training EBMs marginally but nearly consistently, presumably because the optimization of joint-training is directly related to the targeted task, while pre-training does not.","PeriodicalId":156116,"journal":{"name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127155266","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

Graph-Based Transform Based on Neural Networks for Intra-Prediction of Imaging Data 基于神经网络的图像数据内预测图变换

2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596317

Debaleena Roy, T. Guha, V. Sanchez

引用次数: 1

Detecting Cover Songs with Pitch Class Key-Invariant Networks 用音高类键不变网络检测翻唱歌曲

2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596389

K. O'Hanlon, Emmanouil Benetos, S. Dixon

引用次数: 3

Bayesradar : Bayesian Metric-Kalman Filter Learning for Improved and Reliable Radar Target Classification Bayesradar:改进可靠雷达目标分类的贝叶斯度量-卡尔曼滤波学习

2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596290

Anand Dubey, Avik Santra, Jonas Fuchs, Maximilian Lübke, R. Weigel, F. Lurz

{"title":"Bayesradar : Bayesian Metric-Kalman Filter Learning for Improved and Reliable Radar Target Classification","authors":"Anand Dubey, Avik Santra, Jonas Fuchs, Maximilian Lübke, R. Weigel, F. Lurz","doi":"10.1109/mlsp52302.2021.9596290","DOIUrl":"https://doi.org/10.1109/mlsp52302.2021.9596290","url":null,"abstract":"Automotive radar sensors offer a promising and effective modality for perception and assessment of the surrounding environment. A key element of environment sensing in automotive radars is the reliable detection, classification and tracking of vulnerable road users such as pedestrians and cyclists. In this paper, we propose an integrated Bayesian framework dubbed BayesRadar, which improves the overall classification accuracy by tracking the embedding vector of a neural network and its prediction uncertainty via recursive Kalman filtering over time. Apart from the classification accuracy of a model, a critical measure includes the analysis of statistical confidence over the target class score. Such measures for predicting the true correctness likelihood of the classification estimates are essential in safety-critical automotive applications. Therefore, in this paper, we present and evaluate the classification, embedding cluster score and statistical confidence performance of the proposed framework in the context of classifying vulnerable road users compared to state-of-art deep learning approaches. Furthermore, we demonstrate superior performance of the BayesRadar for unseen classes compared to long short-term memory based temporal tracking of the embedding vectors.","PeriodicalId":156116,"journal":{"name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121708541","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

FBR-CNN: A Feedback Recurrent Network for Video Saliency Detection 一种用于视频显著性检测的反馈递归网络

2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596383

Guanqun Ding, Nevrez Imamoglu, Ali Caglayan, M. Murakawa, Ryosuke Nakamura

{"title":"FBR-CNN: A Feedback Recurrent Network for Video Saliency Detection","authors":"Guanqun Ding, Nevrez Imamoglu, Ali Caglayan, M. Murakawa, Ryosuke Nakamura","doi":"10.1109/mlsp52302.2021.9596383","DOIUrl":"https://doi.org/10.1109/mlsp52302.2021.9596383","url":null,"abstract":"Different from the saliency detection on static images, the context and dynamic information from video sequences play an important role in saliency prediction on dynamic scenes. In this work, we propose a novel feedback recurrent network (FBR-CNN) to simultaneously learn the abundant contextual and dynamic features for video saliency detection. In order to learn the dynamic relationship from video frames, we incorporate the recurrent convolutional layers into the standard feed-forward CNN model. With multiple video frames as inputs, the long-term dependence and contextual relevance over time could be strengthen due to the powerful recurrent units. Unlike the feed-forward only CNN models, we propose to feed back the learned CNN features from high-level feedback recurrent blocks (FBR-block) to low-level layers to further enhance the the contextual representations. Experiments on the public video saliency benchmarks demonstrate that the model with feedback connections and recurrent units can dramatically improve the performance of the baseline feedforward structure. Moreover, although the proposed model has few parameters (~6.5 MB), it achieves comparable performance against the existing video saliency approaches.","PeriodicalId":156116,"journal":{"name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122755544","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

Improving Deep Reinforcement Learning for Financial Trading Using Deep Adaptive Group-Based Normalization 基于深度自适应组归一化的金融交易深度强化学习改进

2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596155

A. Nalmpantis, N. Passalis, Avraam Tsantekidis, A. Tefas

{"title":"Improving Deep Reinforcement Learning for Financial Trading Using Deep Adaptive Group-Based Normalization","authors":"A. Nalmpantis, N. Passalis, Avraam Tsantekidis, A. Tefas","doi":"10.1109/mlsp52302.2021.9596155","DOIUrl":"https://doi.org/10.1109/mlsp52302.2021.9596155","url":null,"abstract":"Deep Reinforcement Learning methods have provided powerful tools to train profitable agents for financial trading. However, the noisy and non-stationary nature of financial data often requires carefully designed and tuned input normalization schemes, since otherwise the agents are unable to consistently perform profitable trades. To overcome this limitation, in this work we propose a deep adaptive input normalization approach specifically designed to train DRL agents for financial trading directly using the raw price as input, without any additional pre-processing. The proposed method consists of two trainable neural layers that are designed to perform adaptive normalization, i.e., normalize the input observations after (implicitly) identifying the distribution that was used for generating them. Furthermore, instead of normalizing the whole input at once, the proposed approach performs group-based normalization, which allows for better capturing fine variations in the price trends. Despite being simple to implement and apply, the proposed method can lead to enormous improvements over existing the normalization methods, as demonstrated through the experiments conducted on two challenging FOREX currency pairs.","PeriodicalId":156116,"journal":{"name":"2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)","volume":"2018 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114666005","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

Adversarial Attacks on Multi-Level Fault Detection and Diagnosis Systems 多级故障检测与诊断系统中的对抗性攻击

2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596378

Akram S. Awad, Ismail R. Alkhouri, George K. Atia

引用次数: 1

Detection of Insects in Class-Imbalanced Lidar Field Measurements 类不平衡激光雷达野外测量中昆虫的检测

2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP) Pub Date : 2021-10-25 DOI: 10.1109/mlsp52302.2021.9596143

Trevor C. Vannoy, Trey P. Scofield, Joseph A. Shaw, Riley D. Logan, Bradley M. Whitaker, Elizabeth M. Rehbein

引用次数: 4