PCANet: A Simple Deep Learning Baseline for Image Classification?

14 Apr 2014 Tsung-Han Chan Kui Jia Shenghua Gao Jiwen Lu Zinan Zeng Yi Ma

In this work, we propose a very simple deep learning network for image classification which comprises only the very basic data processing components: cascaded principal component analysis (PCA), binary hashing, and block-wise histograms. In the proposed architecture, PCA is employed to learn multistage filter banks... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Image Classification CIFAR-10 PCANet Percentage correct 78.7 # 101
Image Classification MNIST PCANet Percentage error 0.6 # 16

Methods used in the Paper