PCANet: A Simple Deep Learning Baseline for Image Classification?

Abstract

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. It is followed by simple binary hashing and block histograms for indexing and pooling. This architecture is thus named as a PCA network (PCANet) and can be designed and learned extremely easily and efficiently. For comparison and better understanding, we also introduce and study two simple variations to the PCANet, namely the RandNet and LDANet. They share the same topology of PCANet but their cascaded filters are either selected randomly or learned from LDA. We have tested these basic networks extensively on many benchmark visual datasets for different tasks, such as LFW for face verification, MultiPIE, Extended Yale B, AR, FERET datasets for face recognition, as well as MNIST for hand-written digits recognition. Surprisingly, for all tasks, such a seemingly naive PCANet model is on par with the state of the art features, either prefixed, highly hand-crafted or carefully learned (by DNNs). Even more surprisingly, it sets new records for many classification tasks in Extended Yale B, AR, FERET datasets, and MNIST variations. Additional experiments on other public datasets also demonstrate the potential of the PCANet serving as a simple but highly competitive baseline for texture classification and object recognition.

Cited by in corpus (51)

• DehazeNet: An End-to-End System for Single Image Haze Removal
• Remote Sensing Image Scene Classification: Benchmark and State of the Art
• Deep Face Recognition: A Survey
• A Comprehensive Survey of Deep Learning in Remote Sensing: Theories, Tools and Challenges for the Community
• Deep Learning in Medical Image Registration: A Survey
• Unsupervised Deep Slow Feature Analysis for Change Detection in Multi-Temporal Remote Sensing Images
• Collaborative Unsupervised Domain Adaptation for Medical Image Diagnosis
• Effective Multi-Query Expansions: Collaborative Deep Networks for Robust Landmark Retrieval
• Palmprint Recognition in Uncontrolled and Uncooperative Environment
• Directionally Constrained Fully Convolutional Neural Network For Airborne Lidar Point Cloud Classification
• Person Re-identification in Aerial Imagery
• Poison Ink: Robust and Invisible Backdoor Attack
• RMDL: Random Multimodel Deep Learning for Classification
• Generalized Multi-view Embedding for Visual Recognition and Cross-modal Retrieval
• A Survey of Orthogonal Moments for Image Representation: Theory, Implementation, and Evaluation
• SAR Image Despeckling by Deep Neural Networks: from a pre-trained model to an end-to-end training strategy
• Deep Learning Based Single Sample Per Person Face Recognition: A Survey
• Histogram Layers for Texture Analysis
• Stacking-Based Deep Neural Network: Deep Analytic Network for Pattern Classification
• DCTNet : A Simple Learning-free Approach for Face Recognition
• A Survey of Sample-Efficient Deep Learning for Change Detection in Remote Sensing: Tasks, Strategies, and Challenges
• Multi-Fold Gabor, PCA and ICA Filter Convolution Descriptor for Face Recognition
• Imbalanced Learning-based Automatic SAR Images Change Detection by Morphologically Supervised PCA-Net
• PCA-Initialized Deep Neural Networks Applied To Document Image Analysis
• Fault Diagnosis in Microelectronics Attachment via Deep Learning Analysis of 3D Laser Scans
• Multitask Deep Learning with Spectral Knowledge for Hyperspectral Image Classification
• Robust Adaptive Median Binary Pattern for noisy texture classification and retrieval
• The Labeled Multiple Canonical Correlation Analysis for Information Fusion
• Towards Unconstrained Palmprint Recognition on Consumer Devices: a Literature Review
• CeyMo: See More on Roads -- A Novel Benchmark Dataset for Road Marking Detection
• Genetic Programming-Based Evolutionary Deep Learning for Data-Efficient Image Classification
• An Improvement of Data Classification Using Random Multimodel Deep Learning (RMDL)
• Deep Hybrid Scattering Image Learning
• Diagnosing large-scale stellar magnetic fields using PCA on spectropolarimetric data
• Visual Speech Recognition Using PCA Networks and LSTMs in a Tandem GMM-HMM System
• Deep Learning Techniques for Geospatial Data Analysis
• Bayesian Variable Selection for Globally Sparse Probabilistic PCA
• Provably scale-covariant continuous hierarchical networks based on scale-normalized differential expressions coupled in cascade
• Bias-Eliminated Semantic Refinement for Any-Shot Learning
• L1-(2D)2PCANet: A Deep Learning Network for Face Recognition
• Class specific or shared? A cascaded dictionary learning framework for image classification
• Frank-Wolfe Network: An Interpretable Deep Structure for Non-Sparse Coding
• Cascaded Asymmetric Local Pattern: A Novel Descriptor for Unconstrained Facial Image Recognition and Retrieval
• Local and Global Context-and-Object-part-Aware Superpixel-based Data Augmentation for Deep Visual Recognition
• 3D Binary Signatures
• Representing Noisy Image Without Denoising
• A Hybrid Neural Network Framework and Application to Radar Automatic Target Recognition
• A Committee of Convolutional Neural Networks for Image Classication in the Concurrent Presence of Feature and Label Noise
• Fast Loop Closure Detection via Binary Content
• Self-supervised Latent Space Optimization with Nebula Variational Coding
• Shrinkage Initialization for Smooth Learning of Neural Networks