SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.10093 · 2021

Class-Incremental Learning with Generative Classifiers

arXiv · PDF · Open in the Atlas

Code that ran

2 of 4 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; 2 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/2104.10093.json · badge: /api/ran/2104.10093.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
GMvandeVen/class-incremental-learning canonical (classifier label)
classifier basis: census
2 ran · 2 no recorded run
FunctionStatusWhere it lives
get_data_loader Ran
ran on a synthesized input
GMvandeVen/class-incremental-learning/preprocess_core50.py
code served (permissive licence) · get_code("8fcb2c95a6a3d03e")
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 DataLoader. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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
from torch.utils.data import Dataset, DataLoader
from torch.utils.data.dataloader import default_collate

torch.manual_seed(0)

def label_squeezing_collate_fn(batch):
    x, y = default_collate(batch)
    return (x, y.long().squeeze())

class SimpleDataset(Dataset):
    def __init__(self, num_samples=4, feature_dim=4):
        self.num_samples = num_samples
        self.feature_dim = feature_dim
    
    def __len__(self):
        return self.num_samples
    
    def __getitem__(self, idx):
        x = torch.randn(self.feature_dim)
        y = torch.tensor([idx % 2], dtype=torch.float32)
        return x, y

dataset = SimpleDataset(num_samples=4, feature_dim=4)

ARGS = {
    'dataset': dataset,
    'batch_size': 2,
    'cuda': False,
    'collate_fn': label_squeezing_collate_fn,
    'drop_last': False
}
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 DataLoader — a DataLoader output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataLoader 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
label_squeezing_collate_fn Ran
ran; our contract draft was wrong, not the code
GMvandeVen/class-incremental-learning/preprocess_core50.py
code served (permissive licence) · get_code("2bcd75034219597d")
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
from torch.utils.data.dataloader import default_collate

torch.manual_seed(0)

# Create a small batch of (x, y) tuples
# x: features tensor, y: labels tensor that needs squeezing
batch = [
    (torch.randn(4, 3), torch.tensor([[0]], dtype=torch.float32)),
    (torch.randn(4, 3), torch.tensor([[1]], dtype=torch.float32)),
]

ARGS = {
    "batch": batch
}
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
define_autoencoder Not yet run
unverified (harvested, no recorded run)
GMvandeVen/class-incremental-learning/define_models.py
code served (permissive licence) · get_code("63de4565a29c4d49")
How it ran

no invocation recorded.

download Not yet run
unverified (harvested, no recorded run)
GMvandeVen/class-incremental-learning/preprocess_core50.py
code served (permissive licence) · get_code("247e38928eef8da6")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 4 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 4 later) and 0 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
define_autoencoder 1 other paper
1 later
2410.20768 (2024-10)
Task Confusion and Catastrophic Forgetting in Class-Incremental Learning: A Mathematical Framework for Discriminative and Generative Modelings
download 1 other paper
1 later
2410.20768 (2024-10)
Task Confusion and Catastrophic Forgetting in Class-Incremental Learning: A Mathematical Framework for Discriminative and Generative Modelings
get_data_loader 1 other paper
1 later
2410.20768 (2024-10)
Task Confusion and Catastrophic Forgetting in Class-Incremental Learning: A Mathematical Framework for Discriminative and Generative Modelings
label_squeezing_collate_fn 1 other paper
1 later
2410.20768 (2024-10)
Task Confusion and Catastrophic Forgetting in Class-Incremental Learning: A Mathematical Framework for Discriminative and Generative Modelings

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

Incrementally training deep neural networks to recognize new classes is a challenging problem. Most existing class-incremental learning methods store data or use generative replay, both of which have drawbacks, while 'rehearsal-free' alternatives such as parameter regularization or bias-correction methods do not consistently achieve high performance. Here, we put forward a new strategy for class-incremental learning: generative classification. Rather than directly learning the conditional distribution p(y|x), our proposal is to learn the joint distribution p(x,y), factorized as p(x|y)p(y), and to perform classification using Bayes' rule. As a proof-of-principle, here we implement this strategy by training a variational autoencoder for each class to be learned and by using importance sampling to estimate the likelihoods p(x|y). This simple approach performs very well on a diverse set of continual learning benchmarks, outperforming generative replay and other existing baselines that do not store data.

For agents

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

get_harvested_code_for_paper("2104.10093")
get_code_for_paper("2104.10093")
have("2104.10093")

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

curl https://syntology.ai/api/ran/2104.10093.json

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

[![Syntology run record](https://syntology.ai/api/ran/2104.10093.svg)](https://syntology.ai/paper/2104.10093)

Connect an agent — have() is free.