Can Circulant Attention Reduce Vision Transformer Cost by 7×?

The article reviews the AAAI 2026 paper "Vision Transformers are Circulant Attention Learners", explaining how modeling self‑attention as a Block‑Circulant matrix enables FFT‑based multiplication that cuts the quadratic complexity of standard attention, achieving up to seven‑fold inference speed‑up while preserving accuracy across ImageNet, COCO and ADE20K benchmarks.

BCCB MatrixCirculant AttentionComputer Vision

0 likes · 15 min read

Can Circulant Attention Reduce Vision Transformer Cost by 7×?

AIWalker

Mar 18, 2026 · Artificial Intelligence

7× Faster Inference: Tsinghua’s Huang‑Gao Team Redesigns Vision‑Transformer Attention via Fourier Transforms

The AAAI 2026 paper by Tsinghua’s Huang‑Gao team shows that modeling Vision‑Transformer attention as a Block‑Circulant matrix and computing it with FFT reduces the quadratic complexity to O(N log N), delivering up to seven‑fold real‑world speedups without sacrificing accuracy.

AAAI 2026Circulant MatricesComputer Vision

0 likes · 15 min read

7× Faster Inference: Tsinghua’s Huang‑Gao Team Redesigns Vision‑Transformer Attention via Fourier Transforms

Python Programming Learning Circle

Sep 15, 2022 · Fundamentals

Time Series Analysis in Python: Visualization, FFT, Entropy, PCA and Autocorrelation

This article demonstrates how to analyze and visualize time‑series sensor data in Python using libraries such as NumPy, Pandas, Matplotlib, Seaborn and Scikit‑learn, covering data import, preprocessing, mean‑std plots, boxplots, Fourier transforms, entropy calculation, PCA dimensionality reduction and autocorrelation analysis.

Data visualizationFFTPCA

0 likes · 17 min read

Time Series Analysis in Python: Visualization, FFT, Entropy, PCA and Autocorrelation

DataFunSummit

May 8, 2022 · Artificial Intelligence

Machine Learning‑Based Time Series Forecasting and Anomaly Detection System at JD Search

The article describes JD Search's machine‑learning alert system that combines offline and real‑time training, FFT‑based periodic detection, Prophet forecasting, and DBSCAN anomaly clustering, and explains architectural design, data preprocessing, model optimization, and distributed deployment to improve alert accuracy and response speed.

DBSCANFFTProphet

0 likes · 10 min read

Machine Learning‑Based Time Series Forecasting and Anomaly Detection System at JD Search

DataFunTalk

Apr 24, 2022 · Artificial Intelligence

Machine Learning‑Driven Time Series Forecasting and Anomaly Detection System at JD Search

The article describes JD Search’s machine‑learning‑based time‑series forecasting and anomaly‑detection platform, detailing its overall architecture, offline and real‑time training pipelines, FFT‑based periodicity detection, Prophet forecasting, DBSCAN outlier detection, and distributed optimizations such as Alink integration and load‑balancing strategies.

DBSCANFFTProphet

0 likes · 10 min read

Machine Learning‑Driven Time Series Forecasting and Anomaly Detection System at JD Search

NetEase Cloud Music Tech Team

Sep 17, 2020 · Mobile Development

Android Audio Visualization: From Fourier Transform to Custom Visualizer Implementation

The article explains Android audio visualization by decoding PCM data, applying Fourier and Fast Fourier transforms to obtain frequency spectra, comparing the built‑in Visualizer API with a custom JNI‑based implementation, and detailing FFT processing, smoothing, buffering, and Canvas rendering techniques for smooth, performant visual effects.

AndroidAudio VisualizationBufferQueue

0 likes · 11 min read

Android Audio Visualization: From Fourier Transform to Custom Visualizer Implementation