SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1404.3606 · 2014

PCANet: A Simple Deep Learning Baseline for Image Classification?

arXiv · PDF · Open in the Atlas

Code that ran

2 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 1 failure of our instrument; 1 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/1404.3606.json · badge: /api/ran/1404.3606.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
lucasleesw/PCANet_python_ver community (classifier label)
classifier basis not recorded on the link
2 ran · 1 no recorded run
FunctionStatusWhere it lives
load_CIFAR_batch Ran
ran; our contract draft was wrong, not the code
lucasleesw/PCANet_python_ver/data_loader.py
code served (permissive licence) · get_code("af855a4f120433e9")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
import pickle
import tempfile
import os

# Create a temporary pickle file with CIFAR-like structure
temp_dir = tempfile.mkdtemp()
temp_file = os.path.join(temp_dir, 'test_batch')

# Create a mock CIFAR batch dictionary
mock_data = {
    b'data': np.random.randint(0, 256, size=(10000, 3072), dtype=np.uint8),
    b'labels': np.random.randint(0, 10, size=10000, dtype=np.int64)
}

# Save to pickle file
with open(temp_file, 'wb') as f:
    pickle.dump(mock_data, f)

ARGS = {
    'filename': temp_file
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
load_mnist Ran
ran on a synthesized input
lucasleesw/PCANet_python_ver/data_loader.py
code served (permissive licence) · get_code("3f56553edd2ec3aa")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import os
import struct
import numpy as np
import tempfile
import shutil

# Create a temporary directory for MNIST files
temp_dir = tempfile.mkdtemp()

def create_mnist_file(path, magic, data):
    """Helper to create a minimal valid MNIST file"""
    with open(path, 'wb') as f:
        f.write(struct.pack('>I', magic))
        if magic == 2049:  # labels file
            f.write(struct.pack('>I', len(data)))
            f.write(data.astype(np.uint8).tobytes())
        elif magic == 2051:  # images file
            f.write(struct.pack('>III', len(data), 28, 28))
            f.write(data.astype(np.uint8).tobytes())

# Create minimal training data (10 samples, 28x28 images)
train_images = np.random.randint(0, 256, (10, 28, 28), dtype=np.uint8)
train_labels = np.array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9], dtype=np.uint8)

# Create minimal test data (5 samples, 28x28 images)
test_images = np.random.randint(0, 256, (5, 28, 28), dtype=np.uint8)
test_labels = np.array([0, 1, 2, 3, 4], dtype=np.uint8)

# Write files
create_mnist_file(os.path.join(temp_dir, 'train-labels-idx1-ubyte'), 2049, train_labels)
create_mnist_file(os.path.join(temp_dir, 'train-images-idx3-ubyte'), 2051, train_images)
create_mnist_file(os.path.join(temp_dir, 't10k-labels-idx1-ubyte'), 2049, test_labels)
create_mnist_file(os.path.join(temp_dir, 't10k-images-idx3-ubyte'), 2051, test_images)

ARGS = {
    'root': temp_dir
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
load_mnist_2_0 Not yet run
unverified (harvested, no recorded run)
lucasleesw/PCANet_python_ver/data_loader.py
code served (permissive licence) · get_code("92ee7e4e2a6fd8f1")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 2 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
load_CIFAR_batch 1 other paper
1 later
1702.08835 (2017-02)
Deep Forest

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1404.3606")
get_code_for_paper("1404.3606")
have("1404.3606")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1404.3606.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1404.3606.svg)](https://syntology.ai/paper/1404.3606)

Connect an agent — have() is free.