paper-with-me

홈 › Papers

DIVERSIFY to Generalize: Learning Generalized Representations for Time Series Classification

2021-09-29 · Wang Lu, Jindong Wang, Yiqiang Chen, Xinwei Sun

Time series classification is an important problem in real world. Due to its nonstationary property that the distribution changes over time, it remains challenging to build models for generalization to unseen distributions. In this paper, we propose to view the time series classification problem from the distribution perspective. We argue that the temporal complexity attributes to the unknown latent distributions within. To this end, we propose DIVERSIFY to learn generalized representations for time series classification. DIVERSIFY takes an iterative process: it first obtains the worst-case distribution scenario via adversarial training, then matches the distributions between all segments. We also present some theoretical insights. Extensive experiments on gesture recognition, speech commands recognition, and sensor-based human activity recognition demonstrate that DIVERSIFY significantly outperforms other baselines while effectively characterizing the latent distributions by qualitative and quantitative analysis.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Activity RecognitionClassificationGesture RecognitionHuman Activity RecognitionTime SeriesTime Series AnalysisTime Series Classification

Similar Papers 제목 키워드 기반

DIVERSIFY: A General Framework for Time Series Out-of-distribution Detection and Generalization

2023-08-04 · Wang Lu, Jindong Wang, Xinwei Sun, Yiqiang Chen 외

Time series remains one of the most challenging modalities in machine learning research. The out-of-distribution (OOD) detection and generalization on time series tend to suffer due to its non-stationary property, i.e., …

Activity RecognitionGesture RecognitionHuman Activity RecognitionOut-of-Distribution Detection+3

Out-of-Distribution Representation Learning for Time Series Classification

2022-09-15 · Wang Lu, Jindong Wang, Xinwei Sun, Yiqiang Chen 외

Time series classification is an important problem in real world. Due to its non-stationary property that the distribution changes over time, it remains challenging to build models for generalization to unseen distributi…

Activity RecognitionClassificationGesture RecognitionHuman Activity Recognition+4

Generalized Gradient Learning on Time Series under Elastic Transformations

2015-02-17 · Brijnesh Jain

The majority of machine learning algorithms assumes that objects are represented as vectors. But often the objects we want to learn on are more naturally represented by other data structures such as sequences and time se…

Dynamic Time WarpingTime SeriesTime Series Analysis

WildNet: Learning Domain Generalized Semantic Segmentation from the Wild

2022-04-04 · CVPR 2022 1 · Suhyeon Lee, Hongje Seong, Seongwon Lee, Euntai Kim

We present a new domain generalized semantic segmentation network named WildNet, which learns domain-generalized features by leveraging a variety of contents and styles from the wild. In domain generalization, the low ge…

Domain GeneralizationSemantic Segmentation

Transparent Networks for Multivariate Time Series

2024-10-14 · Minkyu Kim, Suan Lee, Jinho Kim

Transparent models, which are machine learning models that produce inherently interpretable predictions, are receiving significant attention in high-stakes domains. However, despite much real-world data being collected a…

Additive modelsTime Series