SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1701.03551 · 2017

Cost-Effective Active Learning for Deep Image Classification

arXiv · PDF · Open in the Atlas

Code that ran

7 of 13 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 5 have no contract verdict; 2 failures of our instrument; 6 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/1701.03551.json · badge: /api/ran/1701.03551.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
tueboesen/Active-Learning community (classifier label)
classifier basis not recorded on the link
5 ran · 6 no recorded run
dhaalves/CEAL_keras reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
Laplacian_Euclidian Ran
ran on a synthesized input
tueboesen/Active-Learning/src/Laplacian.py
code served (permissive licence) · get_code("6b32679d4e7eeafe")
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, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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
from scipy.sparse import coo_matrix, csr_matrix

# Set random seed for reproducibility
np.random.seed(0)

# Create small sample data
n_points = 4  # number of data points
n_features = 3  # number of features

# Create feature matrix X: (4, 3)
X = np.random.randn(n_points, n_features).astype(np.float64)

# Create a small adjacency matrix (sparse, CSR format)
# We'll create a simple adjacency with some edges
row_indices = [0, 0, 1, 1, 2, 3]
col_indices = [1, 2, 0, 3, 1, 2]
data = [1.0, 1.0, 1.0, 1.0, 1.0, 1.0]
A = csr_matrix((data, (row_indices, col_indices)), shape=(n_points, n_points))

# Sigma parameter (characteristic distance)
sigma = 1.0

# dt parameter (optional, will default to X.dtype if None)
dt = None

ARGS = {
    'X': X,
    'A': A,
    'sigma': sigma,
    'dt': dt
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
convert_pseudo_to_prob Ran
ran on a synthesized input
tueboesen/Active-Learning/src/Clustering.py
code served (permissive licence) · get_code("ba47c929c1387b18")
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 ndarray, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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
from scipy.special import softmax

# Create a small pseudo probability array
# Shape: (batch_size=2, num_classes=4)
# The constraint is that sum should be close to 0 (pseudo probability)
np.random.seed(0)
v = np.random.randn(2, 4).astype(np.float32)

# Make it a pseudo probability by centering around 0
v = v - np.mean(v, axis=1, keepdims=True)

ARGS = {
    "v": v,
    "use_softmax": False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
least_confidence Ran
ran; our contract draft was wrong, not the code
dhaalves/CEAL_keras/CEAL_keras.py
pointer only (licence: NONE) · get_code("c3a594c0d21d6edd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dhaalves/CEAL_keras when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

random_sampling Ran
ran; our contract draft was wrong, not the code
dhaalves/CEAL_keras/CEAL_keras.py
pointer only (licence: NONE) · get_code("8458148753d45f8b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, dhaalves/CEAL_keras when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

run_active_learning_ms Ran
ran on a synthesized input
tueboesen/Active-Learning/src/active_learning_ms.py
code served (permissive licence) · get_code("42940c1bde5e2eeb")
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 torch
import torch.nn as nn
import torch.nn.functional as F

torch.manual_seed(0)

# Create a minimal neural network
class SimpleNet(nn.Module):
    def __init__(self, num_classes=3):
        super().__init__()
        self.fc = nn.Linear(4, num_classes)
    
    def forward(self, x):
        return self.fc(x)

# Create a minimal config class
class Config:
    def __init__(self):
        self.device = 'cpu'

# Create a minimal dataloader (list of batches)
# Each batch is (images, labels, something, indices)
def create_dataloader():
    batches = []
    # Batch 1: 2 samples, 4 features, 3 classes
    images1 = torch.randn(2, 4)
    labels1 = torch.tensor([0, 1])
    idx1 = torch.tensor([0, 1])
    batches.append((images1, labels1, None, idx1))
    
    # Batch 2: 2 samples, 4 features, 3 classes
    images2 = torch.randn(2, 4)
    labels2 = torch.tensor([2, 0])
    idx2 = torch.tensor([2, 3])
    batches.append((images2, labels2, None, idx2))
    
    return batches

# Construct the arguments
net = SimpleNet(num_classes=3)
config = Config()
dataloader = create_dataloader()
idx_labels = [10, 11]  # Some pre-labeled indices
nlabels = 3  # Number of samples to select
delta = 0.5  # Entropy threshold for pseudo-labeling

ARGS = {
    'dl': dataloader,
    'idx_labels': idx_labels,
    'c': config,
    'net': net,
    'nlabels': nlabels,
    'delta': delta
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — 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
run_passive_learning Ran
ran on a synthesized input
tueboesen/Active-Learning/src/passive_learning.py
code served (permissive licence) · get_code("3bdd62274445a4d6")
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 list, ndim 1, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 random
import numpy as np

# Set seeds for reproducibility
np.random.seed(0)
random.seed(0)

# Create small synthetic data
n_samples = 10  # total number of samples
n_classes = 3   # number of classes

# Create pseudo-probabilities (logits before softmax) with shape (n_samples, n_classes)
# Each row represents logits for one sample across all classes
y = np.random.randn(n_samples, n_classes).astype(np.float32)

# Create initial set of labeled indices (already known labels)
# Start with 2 labeled samples
idx_labels = [0, 1]

# Number of labels to learn per class
nlabels_pr_class = 2

ARGS = {
    "idx_labels": idx_labels,
    "y": y,
    "nlabels_pr_class": nlabels_pr_class,
    "class_balance": False
}
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 list, ndim 1, dtype family int — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
setup_custom_logger Ran
ran on a synthesized input
tueboesen/Active-Learning/src/log.py
code served (permissive licence) · get_code("3360b4747085c822")
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 Logger. 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 logging
import tempfile
import os

# Create a temporary directory for the logfile
temp_dir = tempfile.mkdtemp()
logfile_path = os.path.join(temp_dir, 'test.log')

ARGS = {
    'logfile_loc': logfile_path,
    'mode': 'debug',
    'name': 'test_runner'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Logger — a Logger output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Logger output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
SSL_clustering Not yet run
unverified (harvested, no recorded run)
tueboesen/Active-Learning/src/Clustering.py
code served (permissive licence) · get_code("31f6048b40faa14a")
How it ran

no invocation recorded.

getoeda Not yet run
unverified (harvested, no recorded run)
tueboesen/Active-Learning/src/active_learning_adaptive.py
code served (permissive licence) · get_code("c8d769cdd71c731f")
How it ran

no invocation recorded.

load_cifar10 Not yet run
unverified (harvested, no recorded run)
tueboesen/Active-Learning/src/dataloader.py
code served (permissive licence) · get_code("69536dd4fda5a080")
How it ran

no invocation recorded.

load_mnist Not yet run
unverified (harvested, no recorded run)
tueboesen/Active-Learning/src/dataloader.py
code served (permissive licence) · get_code("3f44d3934b8b9f41")
How it ran

no invocation recorded.

oeda Not yet run
unverified (harvested, no recorded run)
tueboesen/Active-Learning/src/active_learning_adaptive.py
code served (permissive licence) · get_code("1ce9ae10cf0304c1")
How it ran

no invocation recorded.

select_dataset Not yet run
unverified (harvested, no recorded run)
tueboesen/Active-Learning/src/dataloader.py
code served (permissive licence) · get_code("df1c4c44ac14aa1f")
How it ran

no invocation recorded.

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 13 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.

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

Recent successes in learning-based image classification, however, heavily rely on the large number of annotated training samples, which may require considerable human efforts. In this paper, we propose a novel active learning framework, which is capable of building a competitive classifier with optimal feature representation via a limited amount of labeled training instances in an incremental learning manner. Our approach advances the existing active learning methods in two aspects. First, we incorporate deep convolutional neural networks into active learning. Through the properly designed framework, the feature representation and the classifier can be simultaneously updated with progressively annotated informative samples. Second, we present a cost-effective sample selection strategy to improve the classification performance with less manual annotations. Unlike traditional methods focusing on only the uncertain samples of low prediction confidence, we especially discover the large amount of high confidence samples from the unlabeled set for feature learning. Specifically, these high confidence samples are automatically selected and iteratively assigned pseudo-labels. We thus call our framework "Cost-Effective Active Learning" (CEAL) standing for the two advantages.Extensive experiments demonstrate that the proposed CEAL framework can achieve promising results on two challenging image classification datasets, i.e., face recognition on CACD database [1] and object categorization on Caltech-256 [2].

For agents

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

get_harvested_code_for_paper("1701.03551")
get_code_for_paper("1701.03551")
have("1701.03551")

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

curl https://syntology.ai/api/ran/1701.03551.json

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

[![Syntology run record](https://syntology.ai/api/ran/1701.03551.svg)](https://syntology.ai/paper/1701.03551)

Connect an agent — have() is free.