[go: up one dir, main page]

Xu et al., 2021 - Google Patents

Dct-based fast spectral convolution for deep convolutional neural networks

Xu et al., 2021

Document ID
5022775163320180781
Author
Xu Y
Nakayama H
Publication year
Publication venue
2021 International Joint Conference on Neural Networks (IJCNN)

External Links

Snippet

Spectral representations have been introduced into deep convolutional neural networks (CNNs) mainly for accelerating convolutions and mitigating information loss. However, repeated domain transformations and complex arithmetic of commonly-used Fourier …
Continue reading at ieeexplore.ieee.org (other versions)

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06F—ELECTRICAL DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/14—Fourier, Walsh or analogous domain transformations, e.g. Laplace, Hilbert, Karhunen-Loeve, transforms
    • G06F17/141—Discrete Fourier transforms
    • G06F17/142—Fast Fourier transforms, e.g. using a Cooley-Tukey type algorithm
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06F—ELECTRICAL DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/14—Fourier, Walsh or analogous domain transformations, e.g. Laplace, Hilbert, Karhunen-Loeve, transforms
    • G06F17/145—Square transforms, e.g. Hadamard, Walsh, Haar, Hough, Slant transforms
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06K—RECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00—Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/36—Image preprocessing, i.e. processing the image information without deciding about the identity of the image
    • G06K9/46—Extraction of features or characteristics of the image
    • G06K9/4671—Extracting features based on salient regional features, e.g. Scale Invariant Feature Transform [SIFT] keypoints
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06F—ELECTRICAL DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06F—ELECTRICAL DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/30—Information retrieval; Database structures therefor; File system structures therefor
    • G06F17/30861—Retrieval from the Internet, e.g. browsers
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06F—ELECTRICAL DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06F—ELECTRICAL DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/30—Information retrieval; Database structures therefor; File system structures therefor
    • G06F17/30286—Information retrieval; Database structures therefor; File system structures therefor in structured data stores
    • G06F17/30312—Storage and indexing structures; Management thereof
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06F—ELECTRICAL DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/30—Information retrieval; Database structures therefor; File system structures therefor
    • G06F17/30286—Information retrieval; Database structures therefor; File system structures therefor in structured data stores
    • G06F17/30386—Retrieval requests

Similar Documents

Publication Publication Date Title
US10796220B2 (en) Systems and methods for vectorized FFT for multi-dimensional convolution operations
Zhou et al. Review of research on lightweight convolutional neural networks
Xu et al. Dct-based fast spectral convolution for deep convolutional neural networks
US10394929B2 (en) Adaptive execution engine for convolution computing systems
CN108765247B (en) Image processing method, device, storage medium and equipment
Kekre et al. Inception of hybrid wavelet transform using two orthogonal transforms and it's use for image compression
Wang et al. A novel image encryption scheme using chaos and Langton’s Ant cellular automaton
CN109858613B (en) A compression method, system and terminal device for a deep neural network
Park 2D discrete Fourier transform on sliding windows
CN106709441A (en) Convolution theorem based face verification accelerating method
CN110020681A (en) Point cloud feature extracting method based on spatial attention mechanism
Li et al. A image encryption algorithm based on coexisting multi-attractors in a spherical chaotic system
Bahri et al. Image feature extraction algorithm based on CUDA architecture: case study GFD and GCFD
CN110399826B (en) End-to-end face detection and identification method
CN116883679B (en) Ground object extraction method and device based on deep learning
CN115836330A (en) Action identification method based on depth residual error network and related product
Moustafa et al. Acceleration of super-resolution for multispectral images using self-example learning and sparse representation
Yang et al. FDS_2D: rethinking magnitude-phase features for DeepFake detection
Prots’ko Algorithm of Efficient Computation of DCT I–IV Using Cyclic Convolutions
CN118097252A (en) Classification method and device for hyperspectral images
CN110321581A (en) A kind of design method of the two-dimensional Fourier transform IP kernel based on HLS
Xu et al. DCT based information-preserving pooling for deep neural networks
Ulicny et al. Tensor reordering for cnn compression
Xu et al. Shifted spatial-spectral convolution for deep neural networks
CN103345491A (en) Method for quickly obtaining neighborhood by the utilization of Hash dividing barrels