# PCANet: A Simple Deep Learning Baseline for Image Classification?

arXiv: https://arxiv.org/abs/1404.3606 · HTML: https://mlsanity.com/paper/1404.3606/

## Key facts

- Cited by 70 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Apr 2014.

## Built on by (most cited first, 30 of 70)

- [Poison Ink: Robust and Invisible Backdoor Attack](https://mlsanity.com/paper/2108.02488/) (2021)
- [On the Principles of Parsimony and Self-Consistency for the Emergence of Intelligence](https://mlsanity.com/paper/2207.04630/) (2022)
- [Human-Centered Concept Explanations for Neural Networks](https://mlsanity.com/paper/2202.12451/) (2022)
- [coVariance Neural Networks](https://mlsanity.com/paper/2205.15856/) (2022)
- [A Physics Informed Neural Network Approach to Solution and Identification of Biharmonic Equations of Elasticity](https://mlsanity.com/paper/2108.07243/) (2021)
- [Interpretability of Machine Learning: Recent Advances and Future Prospects](https://mlsanity.com/paper/2305.00537/) (2023)
- [Neural Implicit Dictionary via Mixture-of-Expert Training](https://mlsanity.com/paper/2207.03691/) (2022)
- [A Survey of Sample-Efficient Deep Learning for Change Detection in Remote Sensing: Tasks, Strategies, and Challenges](https://mlsanity.com/paper/2502.02835/) (2025)
- [A Survey of Orthogonal Moments for Image Representation: Theory, Implementation, and Evaluation](https://mlsanity.com/paper/2103.14799/) (2021)
- [Synaptic Plasticity Models and Bio-Inspired Unsupervised Deep Learning: A Survey](https://mlsanity.com/paper/2307.16236/) (2023)
- [Activation Learning by Local Competitions](https://mlsanity.com/paper/2209.13400/) (2022)
- [Minimalistic Unsupervised Learning with the Sparse Manifold Transform](https://mlsanity.com/paper/2209.15261/) (2022)
- [Deep Learning for Computer Vision based Activity Recognition and Fall Detection of the Elderly: a Systematic Review](https://mlsanity.com/paper/2401.11790/) (2024)
- [Orthogonal SVD Covariance Conditioning and Latent Disentanglement](https://mlsanity.com/paper/2212.05599/) (2022)
- [Deep Learning in Palmprint Recognition-A Comprehensive Survey](https://mlsanity.com/paper/2501.01166/) (2025)
- [UltraFast-LiNET: Light-weight multi-scale shift convolutional network for real-time low-light image enhancement](https://mlsanity.com/paper/2512.02965/) (2025)
- [Fusion or Confusion? Multimodal Complexity Is Not All You Need](https://mlsanity.com/paper/2512.22991/) (2025)
- [VisGraphNet: a complex network interpretation of convolutional neural features](https://mlsanity.com/paper/2108.12490/) (2021)
- [Improving Covariance Conditioning of the SVD Meta-layer by Orthogonality](https://mlsanity.com/paper/2207.02119/) (2022)
- [Genetic Programming-Based Evolutionary Deep Learning for Data-Efficient Image Classification](https://mlsanity.com/paper/2209.13233/) (2022)
- [Histogram Layers for Neural Engineered Features](https://mlsanity.com/paper/2403.17176/) (2024)
- [One model to solve them all: 2BSDE families via neural operators](https://mlsanity.com/paper/2511.01125/) (2025)
- [Deep Features for training Support Vector Machine](https://mlsanity.com/paper/2104.03488/) (2021)
- [The Earth Mover's Pinball Loss: Quantiles for Histogram-Valued Regression](https://mlsanity.com/paper/2106.02051/) (2021)
- [Fractal measures of image local features: an application to texture recognition](https://mlsanity.com/paper/2108.12491/) (2021)
- [Artificial Intelligence For Breast Cancer Detection: Trends & Directions](https://mlsanity.com/paper/2110.00942/) (2021)
- [CeyMo: See More on Roads -- A Novel Benchmark Dataset for Road Marking Detection](https://mlsanity.com/paper/2110.11867/) (2021)
- [Texture Representation via Analysis and Synthesis with Generative Adversarial Networks](https://mlsanity.com/paper/2212.09983/) (2022)
- [The Labeled Multiple Canonical Correlation Analysis for Information Fusion](https://mlsanity.com/paper/2103.00359/) (2021)
- [Bias-Eliminated Semantic Refinement for Any-Shot Learning](https://mlsanity.com/paper/2202.04827/) (2022)

## Abstract (arXiv)

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.