Class-incremental Learning for Time Series: Benchmark and Evaluation

• URL: http://arxiv.org/abs/2402.12035v2
• Date: Sat, 3 Aug 2024 13:29:50 GMT
• Title: Class-incremental Learning for Time Series: Benchmark and Evaluation
• Authors: Zhongzheng Qiao, Quang Pham, Zhen Cao, Hoang H Le, P. N. Suganthan, Xudong Jiang, Ramasamy Savitha,
• Abstract summary: We present an overview of the Time Series Class-incremental Learning (TSCIL) problem, highlight its unique challenges, and cover the advanced methodologies. Based on standardized settings, we develop a unified experimental framework that supports the rapid development of new algorithms. Using this framework, we conduct a comprehensive evaluation of various generic and time-series-specific CIL methods in both standard and privacy-sensitive scenarios.
• Score: 24.39008346076859
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Real-world environments are inherently non-stationary, frequently introducing new classes over time. This is especially common in time series classification, such as the emergence of new disease classification in healthcare or the addition of new activities in human activity recognition. In such cases, a learning system is required to assimilate novel classes effectively while avoiding catastrophic forgetting of the old ones, which gives rise to the Class-incremental Learning (CIL) problem. However, despite the encouraging progress in the image and language domains, CIL for time series data remains relatively understudied. Existing studies suffer from inconsistent experimental designs, necessitating a comprehensive evaluation and benchmarking of methods across a wide range of datasets. To this end, we first present an overview of the Time Series Class-incremental Learning (TSCIL) problem, highlight its unique challenges, and cover the advanced methodologies. Further, based on standardized settings, we develop a unified experimental framework that supports the rapid development of new algorithms, easy integration of new datasets, and standardization of the evaluation process. Using this framework, we conduct a comprehensive evaluation of various generic and time-series-specific CIL methods in both standard and privacy-sensitive scenarios. Our extensive experiments not only provide a standard baseline to support future research but also shed light on the impact of various design factors such as normalization layers or memory budget thresholds. Codes are available at https://github.com/zqiao11/TSCIL.

Related papers

• Happy: A Debiased Learning Framework for Continual Generalized Category Discovery [54.54153155039062]
  This paper explores the underexplored task of Continual Generalized Category Discovery (C-GCD) C-GCD aims to incrementally discover new classes from unlabeled data while maintaining the ability to recognize previously learned classes. We introduce a debiased learning framework, namely Happy, characterized by Hardness-aware prototype sampling and soft entropy regularization.
  arXiv  Detail & Related papers  (2024-10-09T04:18:51Z)
• Multi-Label Continual Learning for the Medical Domain: A Novel Benchmark [47.52603262576663]
  We propose a novel benchmark combining the challenges of new class arrivals and domain shifts in a single framework. This benchmark aims to model a realistic CL setting for the multi-label classification problem in medical imaging.
  arXiv  Detail & Related papers  (2024-04-10T09:35:36Z)
• Few-Shot Class-Incremental Learning via Training-Free Prototype Calibration [67.69532794049445]
  We find a tendency for existing methods to misclassify the samples of new classes into base classes, which leads to the poor performance of new classes. We propose a simple yet effective Training-frEE calibratioN (TEEN) strategy to enhance the discriminability of new classes.
  arXiv  Detail & Related papers  (2023-12-08T18:24:08Z)
• Multivariate Time Series Early Classification Across Channel and Time Dimensions [3.5786621294068373]
  We propose a more flexible early classification pipeline that offers a more granular consideration of input channels. Our method can enhance the early classification paradigm by achieving improved accuracy for equal input utilization.
  arXiv  Detail & Related papers  (2023-06-26T11:30:33Z)
• Large-scale Pre-trained Models are Surprisingly Strong in Incremental Novel Class Discovery [76.63807209414789]
  We challenge the status quo in class-iNCD and propose a learning paradigm where class discovery occurs continuously and truly unsupervisedly. We propose simple baselines, composed of a frozen PTM backbone and a learnable linear classifier, that are not only simple to implement but also resilient under longer learning scenarios.
  arXiv  Detail & Related papers  (2023-03-28T13:47:16Z)
• Fast Hierarchical Learning for Few-Shot Object Detection [57.024072600597464]
  Transfer learning approaches have recently achieved promising results on the few-shot detection task. These approaches suffer from catastrophic forgetting'' issue due to finetuning of base detector. We tackle the aforementioned issues in this work.
  arXiv  Detail & Related papers  (2022-10-10T20:31:19Z)
• LifeLonger: A Benchmark for Continual Disease Classification [59.13735398630546]
  We introduce LifeLonger, a benchmark for continual disease classification on the MedMNIST collection. Task and class incremental learning of diseases address the issue of classifying new samples without re-training the models from scratch. Cross-domain incremental learning addresses the issue of dealing with datasets originating from different institutions while retaining the previously obtained knowledge.
  arXiv  Detail & Related papers  (2022-04-12T12:25:05Z)
• Bridging Non Co-occurrence with Unlabeled In-the-wild Data for Incremental Object Detection [56.22467011292147]
  Several incremental learning methods are proposed to mitigate catastrophic forgetting for object detection. Despite the effectiveness, these methods require co-occurrence of the unlabeled base classes in the training data of the novel classes. We propose the use of unlabeled in-the-wild data to bridge the non-occurrence caused by the missing base classes during the training of additional novel classes.
  arXiv  Detail & Related papers  (2021-10-28T10:57:25Z)

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.