Lune

AAAI2026Top-tier venue

TFD-Net: Towards Intelligent Time-Frequency Mode Decomposition with Practical Applications

Pingping Pan, Yunjian Zhang, Jinyi Liu

Abstract

Time-frequency analysis (TFA) and mode decomposition for non-stationary signals are research hotspots in the field of signal processing. Current optimization-based decomposition methods require a good initial IF estimate. However, due to the Heisenberg uncertainty, achieving accurate ridge extraction from the time-frequency representation (TFR) necessitates empirical parameter adjustments. In this paper, we propose the TFD-Net framework, which takes time-series signals as inputs and adaptively conducts TFR construction and mode decomposition. Specifically, the framework integrates a physically interpretable TFA encoder and a query-based mode decomposition decoder. The highlights of this study include exploring the mathematical equivalence between deep convolutional operators and classical TFA methods. This enables the extraction of multi-scale features for TFR construction and mode separation in a data-driven manner, eliminating the need for signal-specific manual tuning and enhancing adaptability. Finally, simulated and real-world experiments demonstrate TFD-Net's superior performance over several state-of-the-art methods in complex signal processing.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

Builds onCited byLeft to right by year; the more cited, the higher.

Builds on2

  1. Masked-attention Mask Transformer for Universal Image SegmentationBowen Cheng, Ishan Misra, Alexander G. Schwing, Alexander Kirillov et al.CVPR 2022
  2. ECA-Net: Efficient Channel Attention for Deep Convolutional Neural NetworksQilong Wang, Banggu Wu, Pengfei Zhu, Peihua Li et al.CVPR 2020

Related papers

  1. FreDN: Spectral Disentanglement for Time Series Forecasting via Learnable Frequency DecompositionZhongde An, Jinhong You, Jiyanglin Li, Yiming Tang et al.AAAI 2026 · 3 citations
  2. Bridging Time and Frequency: A Joint Modeling Framework for Irregular Multivariate Time Series ForecastingXiangfei Qiu, Kangjia Yan, Xvyuan Liu, Xingjian Wu et al.ICML 2026 · 2 citations
  3. PESD-TSF: A Period-Aware and Explicit Structured Decomposition Framework for Long-Term Time Series ForecastingHua Wang, Xianhao Jiao, Fan ZhangICML 2026
  4. RTFS-Net: Recurrent Time-Frequency Modelling for Efficient Audio-Visual Speech SeparationSamuel Pegg, Kai Li, Xiaolin HuICLR 2024 · 13 citations
  5. FilterNet: Harnessing Frequency Filters for Time Series ForecastingKun Yi, Jingru Fei, Qi Zhang, Hui He et al.NeurIPS 2024 · 140 citations
Dusk over the sea between two cliffs drawn in fine vertical lines