Paper Details

Abstract

Unsupervised time series anomaly detection is critical when labeled data are scarce. Although the Anomaly Transformer achieves strong results on long sequences, our analysis reveals significant degradation on constrained, low-dimensional datasets due to its reliance on a 1D-CNN extractor. To address this, we propose a hybrid encoder combining Temporal Convolutional Network (TCN) and Convolutional Neural Network (CNN) to jointly capture global and local temporal features. Replacing the original embedding with this encoder yields more expressive representations and improves anomaly detection without supervision. Experiments on UCR, ECG, and 2D-Gesture show consistent F1 improvements over the baseline, validating the robustness and generalization of our approach.

Keywords
time series anomaly detection anomaly transformer temporal convolutional networks reconstruction-based learning
Contact Information
Ngu Cong Viet Huynh (Corresponding Author)
FPT University, Vietnam
0968683264

All Authors (2)

Quan Trong Khuu

Affiliation: FPT University

Country: Vietnam

Email: khuutrongquan220405@gmail.com

Phone: 0902357872

Ngu Cong Viet Huynh C

Affiliation: FPT University

Country: Vietnam

Email: nguhcv@fe.edu.vn

Phone: 0968683264