Frequency-Domain Feature Learning

Follow this topic Ask about this topic

Momentum

6 papers in the last four weeks, up 20% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 126

All topics

Structural Bottlenecks on Frequency Representation in End-to-End Audio Models
Jul 9, 2026Nicole Cosme-CliffordAudio Representation Learning Neural Audio Codecs
Yale University New Haven, CT
FourierQK: Spectral Preprocessing of Query-Key Projections Improves Transformer Attention
Jul 8, 2026Athanasios ZerisFrequency-Domain Feature Learning Transformer Attention
Independent Researcher, Athens, Greece.
A Theory of Contrastive Learning with Natural Images
Jul 8, 2026Antonio Torralba, Yair WeissContrastive Learning Frequency-Domain Feature Learning
CSAIL, MIT · School of Computer Science and Engineering, Hebrew University of Jerusalem
SleepBand: Single-Source Domain Generalization for Sleep Staging via Physiologically Structured Spectral Modeling
Jul 6, 2026Zhi Lu, Yang Hu, Yan ChenSleep Stage Classification EEG Decoding
Laboratory of Intelligent Collaborative Computing, University of Electronic Science and Technology of China, Chengdu 611731, China · School of Information Science and Technology, University of Science and Technology of China, Hefei 230026, China · School of Cyber Science and Technology, University of Science and Technology of China, Hefei 230026, China
UniSkip-Mamba: A Frequency-Aware State Space Model for Audio-Visual Temporal Forgery Localization
Jul 5, 2026Cangjin Qiu, Quan Zhang, Dan Jiang +1Frequency-Domain Feature Learning Deepfake Detection
Cangjin Qiu and Ke Zhang are with Soochow University, Suzhou, China. · Quan Zhang and Dan Jiang are with Tsinghua University, Beijing, China.
Fourier Preconditioning for Neural Feature Learning
Jul 2, 2026Preston Pitzer, Anish Pradhan, Harpreet S. DhillonFrequency-Domain Feature Learning Predictive Representation Learning
Frequency Shift Physics-Informed Extreme Learning Machine for Solving High-Frequency Partial Differential Equations
Jul 2, 2026Xiong Xiong, Ruonan Zhai, Zheng Zeng +3PDE Solving Frequency-Domain Feature Learning
School of Mathematics and Statistics, Northwestern Polytechnical University, Xi’an, 710072, China · MIIT Key Laboratory of Dynamics and Control of Complex Systems, Northwestern Polytechnical University, Xi’an, 710072, China · College of Science, Shijiazhuang University, Shijiazhuang, 050035, China +2
I\textsuperscript{2}RiMA: Spectral Riemannian Representation with Temporal Attention for Mental Stress Detection based on EEG Signals
Jul 1, 2026Cheng He, Kunyu Peng, Shangen Han +3Cross-Subject EEG Decoding Electroencephalography
Laboratory of Neural Computing and Intelligent Perception, College of Information Engineering, Capital Normal University, Beijing, China · Karlsruhe Institute of Technology, Germany · School of Psychology, Capital Normal University, Beijing, China
FR-DETR: Frequency and Recurrent Feature Refinement for Robust Object Detection under Adverse Weather
Jun 29, 2026Tuan-Duc Nguyen, Duc-Trong LeFrequency-Domain Feature Learning Detection Transformer
FPT Software AI Center · VNU University of Engineering and Technology
ScaLe-INR: Scale and Learn Implicit Neural Representations
Jun 26, 2026Buwaneka Epakanda, Athulya Ratnayake, Pandula Thennakoon +4Implicit Neural Representations Frequency-Domain Feature Learning
Frequency-Aware Self-Supervised Music Representation Learning
Jun 24, 2026Yicheng Gu, Junan Zhang, Jerry Li +2Audio Representation Learning Frequency-Domain Feature Learning
Spellbrush, Akihabara, Tokyo 101-0021, Japan · Acoustic Lab, Department of Information and Communications Engineering (DICE), Aalto University, Espoo 02150, Finland · School of Data Science, The Chinese University of Hong Kong, Shenzhen, Guangdong 518172, China
From Spatial to Spectral: An Efficient, Frequency-Guided Feature Representation Learner for Small Object Detection
Jun 22, 2026Yuhan Rui, Shihan Qiao, Yibin Lou +7Frequency-Domain Feature Learning Small Object Detection
Southern University of Science and Technology, Shenzhen, China · University of Pennsylvania
Spectral Gating via Damped Oscillations for Adaptive Implicit Neural Representations
Jun 22, 2026Alex Costanzino, Pierluigi Zama Ramirez, Giuseppe Lisanti +1Implicit Neural Representations Frequency-Domain Feature Learning
CVLab, University of Bologna · Ca’ Foscari University of Venice
Temporal-Spectral Alignment with Frequency Adaptation for Source-Free Time-Series Adaptation
Jun 22, 2026Shichang Meng, Linquan Wu, Xuan Ai +1Source-Free Domain Adaptation Domain Adaptation
City University of Hong Kong Hong Kong, China
Efficient Document Tampering Localization with Multi-Level Discrepancy Features and Unified DCT-Quantization Embedding
Jun 21, 2026Mohamed Dhouib, Ye Zhu, Sonia Vanier +1Digital Image Forensics Frequency-Domain Feature Learning
LIX, École Polytechnique, IP Paris, France · DataLab Groupe, Crédit Agricole S.A., France
Frequency-Domain Neural ODEs for Modeling Non-Linear Dynamical Systems
Jun 20, 2026Mohammed Ashraf, Ayman A. El-BadawyFrequency-Domain Feature Learning Nonlinear System Identification
Department of Mechatronics Engineering, German University in Cairo, Cairo, Egypt
FUSE: Frequency-domain Unification and Spectral Energy Alignment for Multi-modal Object Re-Identification
Jun 18, 2026Xuanhao Qi, Tom H. Luan, Yukang Zhang +4Cross-Modal Representation Learning Multimodal Robustness
School of Cyber Science and Engineering, Xi’an Jiaotong University, Xi’an, China · School of Informatics, Xiamen University, Xiamen, China · National University of Singapore, Singapore
Neural Phase Correlation
Jun 16, 2026Cole ReynoldsQuantum System Identification Frequency-Domain Feature Learning
Weyl Labs
TaFD: Threat-Aware Frequency Decoupling for Adversarial Robustness against Heterogeneous Attacks
Jun 16, 2026Mengda Xie, Yiling He, Meie FangAdversarial Training Frequency-Domain Feature Learning
School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, Guangdong, China · Information Security Research Group, University College London, London, United Kingdom
Bridging Spatial And Frequency Views For Disaster Assessment: Benefits And Limitations
Jun 16, 2026Shikha V. Chandel, Yadav Raj Ghimire, Timothy Agboada +1Remote Sensing Image Understanding Building Damage Assessment
College of Science and Technology North Carolina A&T State University Greensboro, NC · Computational Data Science and Engineering North Carolina A&T State University Greensboro, NC
The Discrete-Log Clock: How a Transformer Learns Modular Multiplication
Jun 16, 2026Huu Danh NguyenTransformer Interpretability Frequency-Domain Feature Learning
Stanford University
FATE: Pillar Encoding and Frequency-Aware Training for Event-Based Object Detection
Jun 15, 2026Md Tawheedul Islam Bhuian, Kyoung-Don KangEvent-Based Vision Frequency-Domain Feature Learning
School of Computing State University of New York at Binghamton
The Importance of Phase in Neural Representations: An Internal Oppenheim-Lim Test of Image Classifiers
Jun 15, 2026Alper YıldırımVisual Representation Learning Frequency-Domain Feature Learning
FAConformer: Frequency-Aware Convolutional Transformer for Auditory Attention Decoding
Jun 12, 2026Ziwei Wang, Xingyi He, Tianwang Jia +2Hybrid CNN-Transformer Architectures Neural Decoding
Hubei Key Laboratory of Brain-inspired Intelligent Systems, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, China
Circuit Synchronization Precedes Generalization: A Causal Precursor to Grokking
Jun 11, 2026Achyuthan SivasankarWeight Decay Frequency-Domain Feature Learning
New York University
BASENet: Band-Adapted Speech Enhancement Network with Cross-Band Attention
Jun 10, 2026Damien Martins Gomes, François CapmanFrequency-Domain Feature Learning Speech Enhancement
Thales SIX GTS, FRANCE
MFEN:Multi-Frequency Expert Network for Visible-Infrared Person Re-ID
Jun 10, 2026Xulin Li, Yan Lu, Bin Liu +4Frequency-Domain Feature Learning Person Re-Identification
University of Science and Technology of China, China · Anhui Province Key Laboratory of Digital Security, China · The Chinese University of Hong Kong, China
FreqKD: Frequency-Decoupled Cross-Modal Knowledge Distillation for Infrared Object Detection
Jun 10, 2026Keval Thaker, Venkatraman Narayanan, Abdalmalek Aburaddaha +1Cross-Modal Knowledge Distillation Multispectral Object Detection
University of Michigan-Dearborn 4901 Evergreen Rd Dearborn, MI 48128, USA
PF-Trans: Physics-Embedded Frequency-Aware Transformer for Spectral Reconstruction
Jun 9, 2026Yuzhe Gui, Tianzhu Liu, Yanfeng Gu +1Frequency-Domain Feature Learning Hyperspectral Imaging
Harbin Institute of Technology 150001 Harbin, China
Frequency Decoupled Framework for Screen Content Image Super-Resolution
Jun 8, 2026Xufei Wang, Qicheng Zhang, Qi Wu +2Implicit Neural Representations Frequency-Domain Feature Learning
School of Electronic and Information Engineering, Anhui University, Hefei 230039, China

Jul 9, 2026, cs.SDJ/K move · Enter open · S save

Structural Bottlenecks on Frequency Representation in End-to-End Audio Models

Nicole Cosme-Clifford

Yale University New Haven, CT

Audio Representation Learning Neural Audio Codecs Frequency-Domain Feature Learning Neural Network Interpretability

Open paper AskPDF arXiv

End-to-end neural audio models achieve high-fidelity compression and generation. We might read that performance as evidence they directly represent interpretable features such as pitch and timbre, but a model can produce plausible outputs without doing so. A model may encode these features in any reachable basis, but regardless of which, the features are well described as compositions of time-frequency-localized primitives. Whether state-of-the-art encoders preserve access to these primitives, and thus to compositions of them, remains unclear. Through theoretical analysis and controlled experiments, we show that several state-of-the-art strided convolutional encoders impose two structural bottlenecks, both predictable from architecture and signal structure, on access to these primitives: (1) they collapse primitives into alias equivalence classes, establishing a bound on representational capacity, and (2) they limit the frequency resolution available to learned filters, restricting separability. For well structured data, we find collapse rates of 31-35% and filter bandwidths 10-35x above the theoretical resolution bound, confirming that both bottlenecks arise under realistic signal conditions. We then introduce Gabor Latent Refactorization (GLRF), a lightweight post-hoc intervention that re-expresses encoder latents in a frequency-localized basis, reducing filter bandwidths from 10-35x to 1.5-3x of the theoretical resolution bound while preserving reconstruction fidelity and improving control over attributes like pitch. These results show that the encoders in question predictably degrade access to frequency-localized primitives, entangling the features that depend on them, and that a lightweight, retraining-free intervention can recover much of that access, improving steerability and interpretability.

Momentum

Related topics

Latest papers 126