DeepAI AI Chat
Log In Sign Up

FrequentNet : A New Deep Learning Baseline for Image Classification

by   Yifei Li, et al.

In this paper, we generalize the idea from the method called "PCANet" to achieve a new baseline deep learning model for image classification. Instead of using principal component vectors as the filter vector in "PCANet", we use basis vectors in discrete Fourier analysis and wavelets analysis as our filter vectors. Both of them achieve comparable performance to "PCANet" in benchmark datasets. It is noticeable that our algorithms do not require any optimization techniques to get those basis.


page 4

page 6


DCTNet : A Simple Learning-free Approach for Face Recognition

PCANet was proposed as a lightweight deep learning network that mainly l...

Color Image Classification via Quaternion Principal Component Analysis Network

The Principal Component Analysis Network (PCANet), which is one of the r...

From Principal Subspaces to Principal Components with Linear Autoencoders

The autoencoder is an effective unsupervised learning model which is wid...

Improving Sparse Representation-Based Classification Using Local Principal Component Analysis

Sparse representation-based classification (SRC), proposed by Wright et ...

PCANet: A Simple Deep Learning Baseline for Image Classification?

In this work, we propose a very simple deep learning network for image c...

Deep Spatial Pyramid: The Devil is Once Again in the Details

In this paper we show that by carefully making good choices for various ...

Deep Geometric Moment

Deep networks for image classification often rely more on texture inform...