Frequency-Domain Feature Learning

Ask about this topic

Overview

Frequency-domain feature learning studies how models represent patterns at different spatial or temporal frequencies, from periodic trends and rhythms to edges and fine textures. Common approaches use FFT, STFT, DCT, wavelets, or learned filter banks, combined with band-specific branches, spectral attention, adaptive filtering, or fusion with time- and spatial-domain features. These methods are applied to forecasting, image and audio tasks, EEG, graph learning, and inverse problems, while theoretical work examines why models learn some frequencies before others. A central tension is that low-frequency emphasis can capture global structure and improve stability but may lose fine detail; fixed spectral choices, phase and amplitude cues, and band balances do not transfer equally across tasks or domains.

Latest papers

CardsList

195 papers12 papers in the last four weeks, up 9% on the four weeks before. 0.1% of all new papers.

  1. Frame2Freq: Spectral Adapters for Fine-Grained Video Understanding

    Feb 21, 2026Thinesh Thiyakesan Ponbagavathi, Constantin Seibold, Alina RoitbergVideo Action RecognitionVision Foundation Model Adaptation

    Institute for Artificial Intelligence, University of Stuttgart, Germany · Intelligent Assistive Systems Lab, University of Hildesheim · University Hospital Heidelberg, Diagnostic and Interventional Radiology

  2. On the Mechanism and Dynamics of Modular Addition: Fourier Features, Lottery Ticket, and Grokking

    Feb 18, 2026Jianliang He, Leda Wang, Siyu Chen +1Lottery Ticket HypothesisModular Addition

    Department of Statistics and Data Science, Yale University

  3. ASPEN: Spectral-Temporal Fusion for Cross-Subject Brain Decoding

    Feb 18, 2026Megan Lee, Seung Ha Hwang, Inhyeok Choi +3Cross-Subject EEG DecodingBrain-Computer Interfaces

    Carnegie Mellon University, Pittsburgh, PA, USA · Kyung Hee University, Yongin, South Korea · Korea Advanced Institute of Science and Technology, Deajeon, South Korea +1

  4. FTimeXer: Frequency-aware Time-series Transformer with Exogenous variables for Robust Carbon Footprint Forecasting

    Feb 16, 2026Qingzhong Li, Yue Hu, Zhou Long +3Time Series ForecastingTime Series Transformers

    School of Software, Xinjiang University, Urumqi, China · Xinjiang Key Laboratory of Intelligent Computing and Smart Applications, School of Software, Xinjiang University, Urumqi 830046, China

  5. Dynamic High-frequency Convolution for Infrared Small Target Detection

    Feb 3, 2026Ruojing Li, Chao Xiao, Qian Yin +5Dynamic ConvolutionFrequency-Domain Feature Learning

    The authors are with the College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China.

  6. Mechanistic Evidence for Spectral Structures in Prior-Data Fitted Networks

    Jan 29, 2026Kaustubh Sharma, Srijan Tiwari, Ojasva Nema +1Prior-Data Fitted NetworksNeural Network Interpretability

    Indian Institute of Technology Roorkee, India

  7. Variational Mixture of Graph Neural Experts for Alzheimer's Disease Recognition across Frequency Bands in EEG Brain Networks

    Oct 13, 2025Jun-En Ding, Anna Zilverstand, Shihao Yang +2Alzheimer's DiseaseElectroencephalography

    Department of Industrial and Systems Engineering, Rutgers University, Piscataway, NJ, USA · Department of Psychiatry and Behavioral Sciences, University of Minnesota, Minneapolis, MN, USA · Institute of Brain Science, College of Medicine, National Yang-Ming Chiao Tung University, Taipei City, Taiwan

  8. A Spatial-Spectral-Frequency Interactive Network for Multimodal Remote Sensing Classification

    Oct 6, 2025Hao Liu, Yunhao Gao, Wei Li +3Remote Sensing Image UnderstandingFrequency-Domain Feature Learning

    Department of Information Engineering and Computer Science, University of Trento, 38123 Trento, Italy · School of Information and Electronics, Beijing Institute of Technology, Beijing 100081, China · Beijing Key Laboratory of Fractional Signals and Systems, Beijing Institute of Technology, Beijing 100081, China +3

  9. FMC-DETR: Frequency-Decoupled Multi-Domain Coordination for Aerial-View Object Detection

    Sep 27, 2025Ben Liang, Hongguang Wei, Yuan Liu +4Aerial Object DetectionRemote Sensing Small Object Detection

    School of Electronic Engineering and Optoelectronic Technology, Nanjing University of Science and Technology, Nanjing 210094, China · State Key Laboratory of Extreme Environment Optoelectronic Dynamic Measurement Technology and Instrument, Nanjing 210094, China

  10. Frequency-Domain Decomposition and Recomposition for Robust Audio-Visual Segmentation

    Sep 23, 2025Kai Peng, Yunzhe Shen, Miao Zhang +6Audio-Visual UnderstandingMultimodal Semantic Segmentation

    Dalian University of Technology, Dalian 116024, China · the School of Medicine, Yale University, New Haven, CT 06520 USA · the Department of Electrical and Computer Engineering, University of Alberta, Edmonton, AB T5V 1A4, Canada

  11. Employing Discrete Fourier Transform in Representation Learning

    Jun 7, 2025Raoof HojatJalali, Edmondo TrentinVisual Representation LearningFrequency-Domain Feature Learning

    Universit‘a di Siena, Italy · DIISM, Universit‘a di Siena, Italy

  12. BEAT: Balanced Frequency Adaptive Tuning for Long-Term Time-Series Forecasting

    Jan 31, 2025Zhixuan Li, Naipeng Chen, Seonghwa Choi +2Long-Term Time Series ForecastingFrequency-Domain Time Series Modeling

    College of Computing and Data Science, Nanyang Technological University, Singapore · Department of Electrical and Electronic Engineering, Yonsei University, Korea

  13. Band-Attention Modulation Network for Robust Face Forgery Detection

    Apr 9, 2024Zhida Zhang, Wenkui Yang, Xinlei Ma +2Image Corruption RobustnessImage Forgery Detection

    University of Chinese Academy of Sciences, Beijing, China · MAIS & CRIPAC, Institute of Automation, Chinese Academy of Sciences, Beijing, China

  14. FreDF: Learning to Forecast in the Frequency Domain

    Feb 4, 2024Hao Wang, Licheng Pan, Zhichao Chen +6Frequency-Domain Feature LearningTime Series Forecasting

    Department of Control Science and Engineering, Zhejiang University · School of Automation, Central South University · Trust and Safety Team, TikTok Sydney, ByteDance Inc. +3

  15. Theory of the Frequency Principle for General Deep Neural Networks

    Jun 21, 2019Tao Luo, Zheng Ma, Zhi-Qin John Xu +1Frequency-Domain Feature LearningNeural Network Training Dynamics

    Department of Mathematics, Zheng Ma Purdue University · Department of Mathematics, Purdue University · New York University Abu Dhabi and Courant Institute