Hi-WaveTST: A Hybrid High-Frequency Wavelet-Transformer for Time-Series Classification

• URL: http://arxiv.org/abs/2511.01254v1
• Date: Mon, 03 Nov 2025 05:55:31 GMT
• Title: Hi-WaveTST: A Hybrid High-Frequency Wavelet-Transformer for Time-Series Classification
• Authors: Huseyin Goksu,
• Abstract summary: We propose Hi-WaveTST, a novel Hybrid architecture that augments the original temporal patch with a learnable, High-Frequency wavelet feature stream.<n>Our model achieves a mean accuracy of 93.38 percent plus-minus 0.0043, significantly outperforming the SOTA PatchTST baseline (92.59 percent plus-minus 0.0039)<n>A comprehensive ablation study proves that every component of our design-the hybrid architecture, the deep high-frequency wavelet decomposition, and the learnable GeM pooling-is essential for this state-of-the-art performance.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Transformers have become state-of-the-art (SOTA) for time-series classification, with models like PatchTST demonstrating exceptional performance. These models rely on patching the time series and learning relationships between raw temporal data blocks. We argue that this approach is blind to critical, non-obvious high-frequency information that is complementary to the temporal dynamics. In this letter, we propose Hi-WaveTST, a novel Hybrid architecture that augments the original temporal patch with a learnable, High-Frequency wavelet feature stream. Our wavelet stream uses a deep Wavelet Packet Decomposition (WPD) on each patch and extracts features using a learnable Generalized Mean (GeM) pooling layer. On the UCI-HAR benchmark dataset, our hybrid model achieves a mean accuracy of 93.38 percent plus-minus 0.0043, significantly outperforming the SOTA PatchTST baseline (92.59 percent plus-minus 0.0039). A comprehensive ablation study proves that every component of our design-the hybrid architecture, the deep high-frequency wavelet decomposition, and the learnable GeM pooling-is essential for this state-of-the-art performance.

Related papers

• WaveFormer: Frequency-Time Decoupled Vision Modeling with Wave Equation [24.13944601660532]
  Vision modeling has advanced rapidly with Transformers, whose attention mechanisms capture visual dependencies but lack a principled account of how semantic information propagates spatially.<n>We revisit this problem from a wave-based perspective, treating feature maps as spatial signals whose evolution over an internal propagation time is governed by an underdamped wave equation.<n>We propose a family of WaveFormer models as drop-in replacements for standard ViTs and CNNs, achieving competitive accuracy across image classification, object detection, and semantic segmentation.
  arXiv  Detail & Related papers  (2026-01-13T14:47:22Z)
• FLaTEC: Frequency-Disentangled Latent Triplanes for Efficient Compression of LiDAR Point Clouds [52.997038111673966]
  FLaTEC is a frequency-aware compression model that enables the compression of a full scan with high compression ratios.<n>We convert voxelized embeddings into triplane representations to reduce sparsity, computational cost, and storage requirements.<n>Our method achieves state-of-the-art rate-distortion performance and outperforms the standard codecs by 78% and 94% in BD-rate on both datasets.
  arXiv  Detail & Related papers  (2025-11-25T08:37:49Z)
• AWEMixer: Adaptive Wavelet-Enhanced Mixer Network for Long-Term Time Series Forecasting [12.450099337354017]
  We propose AWEMixer, an Adaptive Wavelet-Enhanced Mixer Network.<n>A Frequency Router designs to utilize the global periodicity pattern achieved by Fast Fourier Transform to adaptively weight localized wavelet subband.<n>A Coherent Gated Fusion Block to achieve selective integration of prominent frequency features with multi-scale temporal representation.
  arXiv  Detail & Related papers  (2025-11-06T11:27:12Z)
• EntroPE: Entropy-Guided Dynamic Patch Encoder for Time Series Forecasting [50.794700596484894]
  We propose EntroPE (Entropy-Guided Dynamic Patch), a novel, temporally informed framework that dynamically detects transition points via conditional entropy.<n>This preserves temporal structure while retaining the computational benefits of patching.<n> Experiments across long-term forecasting benchmarks demonstrate that EntroPE improves both accuracy and efficiency.
  arXiv  Detail & Related papers  (2025-09-30T12:09:56Z)
• Freqformer: Image-Demoiréing Transformer via Efficient Frequency Decomposition [83.40450475728792]
  We present Freqformer, a Transformer-based framework specifically designed for image demoir'eing through targeted frequency separation.<n>Our method performs an effective frequency decomposition that explicitly splits moir'e patterns into high-frequency spatially-localized textures and low-frequency scale-robust color distortions.<n>Experiments on various demoir'eing benchmarks demonstrate that Freqformer achieves state-of-the-art performance with a compact model size.
  arXiv  Detail & Related papers  (2025-05-25T12:23:10Z)
• A Wavelet-based Stereo Matching Framework for Solving Frequency Convergence Inconsistency [9.668149257194887]
  We propose a wavelet-based stereo matching framework (Wavelet-Stereo) for solving frequency convergence inconsistency.<n>By processing high and low frequency components separately, our framework can simultaneously refine high-frequency information in edges and low-frequency information in smooth regions.
  arXiv  Detail & Related papers  (2025-05-23T15:28:03Z)
• WaveHiTS: Wavelet-Enhanced Hierarchical Time Series Modeling for Wind Direction Nowcasting in Eastern Inner Mongolia [3.1789338656073305]
  This paper presents a novel model, WaveHiTS, which integrates wavelet transform with Neural Hierarchical Interpolation for Time Series.<n>Our approach decomposes wind direction into U-V components, applies wavelet transform to capture multi-scale frequency patterns, and utilizes a hierarchical structure to model temporal dependencies.<n> Experiments conducted on real-world meteorological data from Inner Mongolia, China demonstrate that WaveHiTS significantly outperforms deep learning models.
  arXiv  Detail & Related papers  (2025-04-09T02:15:48Z)
• Enhancing Foundation Models for Time Series Forecasting via Wavelet-based Tokenization [74.3339999119713]
  We develop a wavelet-based tokenizer that allows models to learn complex representations directly in the space of time-localized frequencies.<n>Our method first scales and decomposes the input time series, then thresholds and quantizes the wavelet coefficients, and finally pre-trains an autoregressive model to forecast coefficients for the forecast horizon.
  arXiv  Detail & Related papers  (2024-12-06T18:22:59Z)
• FlowTS: Time Series Generation via Rectified Flow [67.41208519939626]
  FlowTS is an ODE-based model that leverages rectified flow with straight-line transport in probability space.<n>For unconditional setting, FlowTS achieves state-of-the-art performance, with context FID scores of 0.019 and 0.011 on Stock and ETTh datasets.<n>For conditional setting, we have achieved superior performance in solar forecasting.
  arXiv  Detail & Related papers  (2024-11-12T03:03:23Z)
• Accelerating High-Fidelity Waveform Generation via Adversarial Flow Matching Optimization [37.35829410807451]
  This paper introduces PeriodWave-Turbo, a high-fidelity and high-efficient waveform generation model via adversarial flow matching optimization. It only requires 1,000 steps of fine-tuning to achieve state-of-the-art performance across various objective metrics. By scaling up the backbone of PeriodWave from 29M to 70M parameters for improved generalization, PeriodWave-Turbo achieves unprecedented performance.
  arXiv  Detail & Related papers  (2024-08-15T08:34:00Z)
• WaveMamba: Spatial-Spectral Wavelet Mamba for Hyperspectral Image Classification [3.5302264121619094]
  This paper introduces WaveMamba, a novel approach that integrates wavelet transformation with the spatial-spectral Mamba architecture to enhance HSI classification. WaveMamba surpasses existing models, achieving an accuracy improvement of 4.5% on the University of Houston dataset and a 2.0% increase on the Pavia University dataset.
  arXiv  Detail & Related papers  (2024-08-02T12:44:07Z)
• Inception Transformer [151.939077819196]
  Inception Transformer, or iFormer, learns comprehensive features with both high- and low-frequency information in visual data. We benchmark the iFormer on a series of vision tasks, and showcase that it achieves impressive performance on image classification, COCO detection and ADE20K segmentation.
  arXiv  Detail & Related papers  (2022-05-25T17:59:54Z)
• Real Time Speech Enhancement in the Waveform Domain [99.02180506016721]
  We present a causal speech enhancement model working on the raw waveform that runs in real-time on a laptop CPU. The proposed model is based on an encoder-decoder architecture with skip-connections. It is capable of removing various kinds of background noise including stationary and non-stationary noises.
  arXiv  Detail & Related papers  (2020-06-23T09:19:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.