Conditional Generation of Periodic Signals with Fourier-Based Decoder
arXiv:2110.12365
Abstract
Periodic signals play an important role in daily lives. Although conventional sequential models have shown remarkable success in various fields, they still come short in modeling periodicity; they either collapse, diverge or ignore details. In this paper, we introduce a novel framework inspired by Fourier series to generate periodic signals. We first decompose the given signals into multiple sines and cosines and then conditionally generate periodic signals with the output components. We have shown our model efficacy on three tasks: reconstruction, imputation and conditional generation. Our model outperforms baselines in all tasks and shows more stable and refined results.
NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications Poster Presentation
References in corpus (5)
- Language Models are Few-Shot Learners
- Zero-Shot Text-to-Image Generation
- Conditional Time Series Forecasting with Convolutional Neural Networks
- Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs
- T-CGAN: Conditional Generative Adversarial Network for Data Augmentation in Noisy Time Series with Irregular Sampling