Time series classification from scratch with deep neural networks: A strong baseline

TLDR

The paper proposes a simple yet strong baseline for time series classification using deep neural networks from scratch. The baseline consists of end‑to‑end deep neural networks—specifically a Fully Convolutional Network with global average pooling that supports Class Activation Maps—alongside an analysis of generalization, learned features, and network semantics. The Fully Convolutional Network outperforms state‑of‑the‑art methods, and the ResNet variant is competitive, offering a practical solution and a solid foundation for future work.

Abstract

We propose a simple but strong baseline for time series classification from scratch with deep neural networks. Our proposed baseline models are pure end-to-end without any heavy preprocessing on the raw data or feature crafting. The proposed Fully Convolutional Network (FCN) achieves premium performance to other state-of-the-art approaches and our exploration of the very deep neural networks with the ResNet structure is also competitive. The global average pooling in our convolutional model enables the exploitation of the Class Activation Map (CAM) to find out the contributing region in the raw data for the specific labels. Our models provides a simple choice for the real world application and a good starting point for the future research. An overall analysis is provided to discuss the generalization capability of our models, learned features, network structures and the classification semantics.