CRITS: Convolutional Rectifier for Interpretable Time Series Classification

• URL: http://arxiv.org/abs/2506.12042v1
• Date: Sat, 24 May 2025 08:34:08 GMT
• Title: CRITS: Convolutional Rectifier for Interpretable Time Series Classification
• Authors: Alejandro Kuratomi, Zed Lee, Guilherme Dinis Chaliane Junior, Tony Lindgren, Diego García Pérez,
• Abstract summary: We propose Convolutional Rectifier for Interpretable Time Series Classification, or CRITS, as an interpretable model for time series classification.<n>We evaluate CRITS on a set of datasets, and study its classification performance and its explanation alignment, sensitivity and understandability.
• Score: 41.18535141696404
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Several interpretability methods for convolutional network-based classifiers exist. Most of these methods focus on extracting saliency maps for a given sample, providing a local explanation that highlights the main regions for the classification. However, some of these methods lack detailed explanations in the input space due to upscaling issues or may require random perturbations to extract the explanations. We propose Convolutional Rectifier for Interpretable Time Series Classification, or CRITS, as an interpretable model for time series classification that is designed to intrinsically extract local explanations. The proposed method uses a layer of convolutional kernels, a max-pooling layer and a fully-connected rectifier network (a network with only rectified linear unit activations). The rectified linear unit activation allows the extraction of the feature weights for the given sample, eliminating the need to calculate gradients, use random perturbations and the upscale of the saliency maps to the initial input space. We evaluate CRITS on a set of datasets, and study its classification performance and its explanation alignment, sensitivity and understandability.

Related papers

• FreSca: Scaling in Frequency Space Enhances Diffusion Models [55.75504192166779]
  This paper explores frequency-based control within latent diffusion models.<n>We introduce FreSca, a novel framework that decomposes noise difference into low- and high-frequency components.<n>FreSca operates without any model retraining or architectural change, offering model- and task-agnostic control.
  arXiv  Detail & Related papers  (2025-04-02T22:03:11Z)
• Studying Classifier(-Free) Guidance From a Classifier-Centric Perspective [100.54185280153753]
  We find that both classifier guidance and classifier-free guidance achieve conditional generation by pushing the denoising diffusion trajectories away from decision boundaries.<n>We propose a generic postprocessing step built upon flow-matching to shrink the gap between the learned distribution for a pretrained denoising diffusion model and the real data distribution.
  arXiv  Detail & Related papers  (2025-03-13T17:59:59Z)
• Adaptive Random Feature Regularization on Fine-tuning Deep Neural Networks [12.992733141210158]
  We propose a simple method called adaptive random feature regularization (AdaRand) AdaRand helps the feature extractors of training models to adaptively change the distribution of feature vectors for downstream classification tasks without auxiliary source information and with reasonable computation costs. Our experiments show that AdaRand outperforms the other fine-tuning regularization, which requires auxiliary source information and heavy computation costs.
  arXiv  Detail & Related papers  (2024-03-15T08:26:59Z)
• Adaptive Graph Convolutional Subspace Clustering [10.766537212211217]
  Spectral-type subspace clustering algorithms have shown excellent performance in many subspace clustering applications. In this paper, inspired by graph convolutional networks, we use the graph convolution technique to develop a feature extraction method and a coefficient matrix constraint simultaneously. We claim that by using AGCSC, the aggregated feature representation of original data samples is suitable for subspace clustering.
  arXiv  Detail & Related papers  (2023-05-05T10:27:23Z)
• Recurrent Spectral Network (RSN): shaping the basin of attraction of a discrete map to reach automated classification [4.724825031148412]
  A novel strategy to automated classification is introduced which exploits a fully trained dynamical system to steer items toward distinct attractors. Non-linear terms act for a transient and allow to disentangle the data supplied as initial condition to the discrete dynamical system. Our novel approach to classification, that we here term Recurrent Spectral Network (RSN), is successfully challenged against a simple test-bed model, created for illustrative purposes, as well as a standard dataset for image processing training.
  arXiv  Detail & Related papers  (2022-02-09T14:59:06Z)
• Motor Imagery Classification based on CNN-GRU Network with Spatio-Temporal Feature Representation [22.488536453952964]
  Recently various deep neural networks have been applied to electroencephalogram (EEG) signal. EEG is a brain signal that can be acquired in a non-invasive way and has a high temporal resolution. As the EEG signal has a high dimension of classification feature space, appropriate feature extraction methods are needed to improve performance.
  arXiv  Detail & Related papers  (2021-07-15T01:05:38Z)
• DAAIN: Detection of Anomalous and Adversarial Input using Normalizing Flows [52.31831255787147]
  We introduce a novel technique, DAAIN, to detect out-of-distribution (OOD) inputs and adversarial attacks (AA) Our approach monitors the inner workings of a neural network and learns a density estimator of the activation distribution. Our model can be trained on a single GPU making it compute efficient and deployable without requiring specialized accelerators.
  arXiv  Detail & Related papers  (2021-05-30T22:07:13Z)
• Coverage probability in wireless networks with determinantal scheduling [1.4502611532302039]
  We propose a new class of algorithms for randomly scheduling network transmissions. We show that, similarly to Aloha, they are also subject to elegant analysis of the coverage probabilities and transmission attempts.
  arXiv  Detail & Related papers  (2020-06-09T04:05:50Z)
• Ensemble Wrapper Subsampling for Deep Modulation Classification [70.91089216571035]
  Subsampling of received wireless signals is important for relaxing hardware requirements as well as the computational cost of signal processing algorithms. We propose a subsampling technique to facilitate the use of deep learning for automatic modulation classification in wireless communication systems.
  arXiv  Detail & Related papers  (2020-05-10T06:11:13Z)
• Spatially Adaptive Inference with Stochastic Feature Sampling and Interpolation [72.40827239394565]
  We propose to compute features only at sparsely sampled locations. We then densely reconstruct the feature map with an efficient procedure. The presented network is experimentally shown to save substantial computation while maintaining accuracy over a variety of computer vision tasks.
  arXiv  Detail & Related papers  (2020-03-19T15:36:31Z)
• Embedding Propagation: Smoother Manifold for Few-Shot Classification [131.81692677836202]
  We propose to use embedding propagation as an unsupervised non-parametric regularizer for manifold smoothing in few-shot classification. We empirically show that embedding propagation yields a smoother embedding manifold. We show that embedding propagation consistently improves the accuracy of the models in multiple semi-supervised learning scenarios by up to 16% points.
  arXiv  Detail & Related papers  (2020-03-09T13:51:09Z)

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.