Class-Specific Attention (CSA) for Time-Series Classification

• URL: http://arxiv.org/abs/2211.10609v1
• Date: Sat, 19 Nov 2022 07:51:51 GMT
• Title: Class-Specific Attention (CSA) for Time-Series Classification
• Authors: Yifan Hao, Huiping Cao, K. Selcuk Candan, Jiefei Liu, Huiying Chen, Ziwei Ma
• Abstract summary: We propose a novel class-specific attention (CSA) module to capture significant class-specific features and improve the overall classification performance of time series. An NN model embedded with the CSA module can improve the base model in most cases and the accuracy improvement can be up to 42%. Our statistical analysis show that the performance of an NN model embedding the CSA module is better than the base NN model on 67% of MTS and 80% of UTS test cases.
• Score: 8.390973438687777
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Most neural network-based classifiers extract features using several hidden layers and make predictions at the output layer by utilizing these extracted features. We observe that not all features are equally pronounced in all classes; we call such features class-specific features. Existing models do not fully utilize the class-specific differences in features as they feed all extracted features from the hidden layers equally to the output layers. Recent attention mechanisms allow giving different emphasis (or attention) to different features, but these attention models are themselves class-agnostic. In this paper, we propose a novel class-specific attention (CSA) module to capture significant class-specific features and improve the overall classification performance of time series. The CSA module is designed in a way such that it can be adopted in existing neural network (NN) based models to conduct time series classification. In the experiments, this module is plugged into five start-of-the-art neural network models for time series classification to test its effectiveness by using 40 different real datasets. Extensive experiments show that an NN model embedded with the CSA module can improve the base model in most cases and the accuracy improvement can be up to 42%. Our statistical analysis show that the performance of an NN model embedding the CSA module is better than the base NN model on 67% of MTS and 80% of UTS test cases and is significantly better on 11% of MTS and 13% of UTS test cases.

Related papers

• Sparse Modular Activation for Efficient Sequence Modeling [94.11125833685583]
  Recent models combining Linear State Space Models with self-attention mechanisms have demonstrated impressive results across a range of sequence modeling tasks. Current approaches apply attention modules statically and uniformly to all elements in the input sequences, leading to sub-optimal quality-efficiency trade-offs. We introduce Sparse Modular Activation (SMA), a general mechanism enabling neural networks to sparsely activate sub-modules for sequence elements in a differentiable manner.
  arXiv  Detail & Related papers  (2023-06-19T23:10:02Z)
• Multiclass classification for multidimensional functional data through deep neural networks [0.22843885788439797]
  We introduce a novel functional deep neural network (mfDNN) as an innovative data mining classification tool. We consider sparse deep neural network architecture with linear unit (ReLU) activation function and minimize the cross-entropy loss in the multiclass classification setup. We demonstrate the performance of mfDNN on simulated data and several benchmark datasets from different application domains.
  arXiv  Detail & Related papers  (2023-05-22T16:56:01Z)
• Continuous time recurrent neural networks: overview and application to forecasting blood glucose in the intensive care unit [56.801856519460465]
  Continuous time autoregressive recurrent neural networks (CTRNNs) are a deep learning model that account for irregular observations. We demonstrate the application of these models to probabilistic forecasting of blood glucose in a critical care setting.
  arXiv  Detail & Related papers  (2023-04-14T09:39:06Z)
• Neural Attentive Circuits [93.95502541529115]
  We introduce a general purpose, yet modular neural architecture called Neural Attentive Circuits (NACs) NACs learn the parameterization and a sparse connectivity of neural modules without using domain knowledge. NACs achieve an 8x speedup at inference time while losing less than 3% performance.
  arXiv  Detail & Related papers  (2022-10-14T18:00:07Z)
• Domain Adaptive Nuclei Instance Segmentation and Classification via Category-aware Feature Alignment and Pseudo-labelling [65.40672505658213]
  We propose a novel deep neural network, namely Category-Aware feature alignment and Pseudo-Labelling Network (CAPL-Net) for UDA nuclei instance segmentation and classification. Our approach outperforms state-of-the-art UDA methods with a remarkable margin.
  arXiv  Detail & Related papers  (2022-07-04T07:05:06Z)
• Animal Behavior Classification via Accelerometry Data and Recurrent Neural Networks [11.099308746733028]
  We study the classification of animal behavior using accelerometry data through various recurrent neural network (RNN) models. We evaluate the classification performance and complexity of the considered models. We also include two state-of-the-art convolutional neural network (CNN)-based time-series classification models in the evaluations.
  arXiv  Detail & Related papers  (2021-11-24T23:28:25Z)
• Improving Time Series Classification Algorithms Using Octave-Convolutional Layers [0.0]
  We experimentally show that by substituting convolutions with OctConv, we significantly improve accuracy for time series classification tasks. In addition, the updated ALSTM-OctFCN performs statistically the same as the top two time series classifers.
  arXiv  Detail & Related papers  (2021-09-28T13:12:09Z)
• Calibrating Class Activation Maps for Long-Tailed Visual Recognition [60.77124328049557]
  We present two effective modifications of CNNs to improve network learning from long-tailed distribution. First, we present a Class Activation Map (CAMC) module to improve the learning and prediction of network classifiers. Second, we investigate the use of normalized classifiers for representation learning in long-tailed problems.
  arXiv  Detail & Related papers  (2021-08-29T05:45:03Z)
• Learning Class Regularized Features for Action Recognition [68.90994813947405]
  We introduce a novel method named Class Regularization that performs class-based regularization of layer activations. We show that using Class Regularization blocks in state-of-the-art CNN architectures for action recognition leads to systematic improvement gains of 1.8%, 1.2% and 1.4% on the Kinetics, UCF-101 and HMDB-51 datasets, respectively.
  arXiv  Detail & Related papers  (2020-02-07T07:27:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.