SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.08536 · ECCV · 2024

Exemplar-free Continual Representation Learning via Learnable Drift Compensation

Joost Van De Weijer, Andrew Bagdanov, Kai Wang, Alex Gomez-Villa, Dipam Goswami, Bartlomiej Twardowski

arXiv · PDF · Open in the Atlas

Code that ran

8 of 16 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (6 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 8 have no contract verdict; 0 failures of our instrument; 8 no recorded run), measured 2026-11-22; 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/2407.08536.json · badge: /api/ran/2407.08536.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
alviur/ldc community
Papers with Code archive
8 ran · 8 no recorded run
FunctionStatusWhere it lives
BasicBlock Ran
ran on a synthesized input · constructed an object; no result was computed
alviur/ldc/LDC_supervised/utils/inc_net.py
pointer only (licence: NONE) · get_code("dbe3fac682109b6d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, alviur/ldc 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.

BiasLayer Ran
ran on a synthesized input
alviur/ldc/LDC_supervised/utils/inc_net.py
pointer only (licence: NONE) · get_code("87398910fe111b52")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, alviur/ldc 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.

Bottleneck Ran
ran on a synthesized input · constructed an object; no result was computed
alviur/ldc/LDC_supervised/utils/inc_net.py
pointer only (licence: NONE) · get_code("ef61c2aa0a4537c4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, alviur/ldc 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.

CifarResNet Ran
ran on a synthesized input · constructed an object; no result was computed
alviur/ldc/LDC_supervised/utils/inc_net.py
pointer only (licence: NONE) · get_code("f01bbae97fc02fe2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, alviur/ldc 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.

ResNet Ran
ran on a synthesized input · constructed an object; no result was computed
alviur/ldc/LDC_supervised/utils/inc_net.py
pointer only (licence: NONE) · get_code("fdd43958e7883a10")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, alviur/ldc 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.

ResNetBasicblock Ran
ran on a synthesized input · constructed an object; no result was computed
alviur/ldc/LDC_supervised/utils/inc_net.py
pointer only (licence: NONE) · get_code("3c716113cca2845d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, alviur/ldc 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.

SimpleLinear Ran
ran on a synthesized input · constructed an object; no result was computed
alviur/ldc/LDC_supervised/utils/inc_net.py
pointer only (licence: NONE) · get_code("7655f8c8144a2115")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, alviur/ldc 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.

resnet20 Ran
ran on a synthesized input
alviur/ldc/LDC_supervised/utils/inc_net.py
pointer only (licence: NONE) · get_code("5ef4da296d6ae98f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, alviur/ldc 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.

BaseNet Not yet run
unverified (harvested, no recorded run)
alviur/ldc/LDC_supervised/utils/inc_net.py
pointer only (licence: NONE) · get_code("90ae5395a0910645")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, alviur/ldc 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. No invocation recorded.

IncrementalNetWithBias Not yet run
unverified (harvested, no recorded run)
alviur/ldc/LDC_supervised/utils/inc_net.py
pointer only (licence: NONE) · get_code("97a66fa3748606c8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, alviur/ldc 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. No invocation recorded.

_resnet Not yet run
unverified (harvested, no recorded run)
alviur/ldc/LDC_supervised/utils/inc_net.py
pointer only (licence: NONE) · get_code("a5cf18333d3ea433")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, alviur/ldc 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. No invocation recorded.

get_convnet Not yet run
unverified (harvested, no recorded run)
alviur/ldc/LDC_supervised/utils/inc_net.py
pointer only (licence: NONE) · get_code("e113d5c01297db61")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, alviur/ldc 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. No invocation recorded.

resnet18_cbam Not yet run
unverified (harvested, no recorded run)
alviur/ldc/LDC_supervised/utils/inc_net.py
pointer only (licence: NONE) · get_code("412e05953cc83f60")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, alviur/ldc 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. No invocation recorded.

resnet18_rep Not yet run
unverified (harvested, no recorded run)
alviur/ldc/LDC_supervised/utils/inc_net.py
pointer only (licence: NONE) · get_code("3280b9194d9b887e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, alviur/ldc 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. No invocation recorded.

resnet34_cbam Not yet run
unverified (harvested, no recorded run)
alviur/ldc/LDC_supervised/utils/inc_net.py
pointer only (licence: NONE) · get_code("8554cc53a70dc32c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, alviur/ldc 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. No invocation recorded.

resnet50_cbam Not yet run
unverified (harvested, no recorded run)
alviur/ldc/LDC_supervised/utils/inc_net.py
pointer only (licence: NONE) · get_code("4eafd11a912aa2f1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, alviur/ldc 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. No invocation recorded.

Also present in other papers' code

Of 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 7 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 0 the same month, 5 later) and 9 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
resnet34_cbam
brick of this paper's assembly: helper
11 other papers
7 dated earlier, 3 later, 1 same year, order not determinable
2309.14062 (2023-09)
FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning
2310.15171 (2023-10)
RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptions
aaai_29079 (2024 (year only))
Dynamic Sub-graph Distillation for Robust Semi-supervised Continual Learning
and 8 more not named here
BasicBlock
brick of this paper's assembly: helper
9 other papers
8 dated earlier, 1 later · 5 only as an assembly brick
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
2002.05709 (2020-02)
A Simple Framework for Contrastive Learning of Visual Representations
2104.10475 (2021-04)
Camouflaged Object Segmentation with Distraction Mining
and 6 more not named here
Bottleneck
brick of this paper's assembly: helper
7 other papers
6 dated earlier, 1 later · 2 only as an assembly brick
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
2104.10475 (2021-04)
Camouflaged Object Segmentation with Distraction Mining
2110.00990 (2021-10)
Hierarchical Kinematic Probability Distributions for 3D Human Shape and Pose Estimation from Images in the Wild
and 4 more not named here
SimpleLinear
brick of this paper's assembly: helper
5 other papers
4 dated earlier, 1 later · 1 only as an assembly brick
2204.04662 (2022-04)
FOSTER: Feature Boosting and Compression for Class-Incremental Learning
2205.13218 (2022-05)
A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning
2308.13305 (2023-08)
Dynamic Residual Classifier for Class Incremental Learning
and 2 more not named here
ResNetBasicblock
brick of this paper's assembly: helper
3 other papers
2 dated earlier, 1 later · 1 only as an assembly brick
2204.04662 (2022-04)
FOSTER: Feature Boosting and Compression for Class-Incremental Learning
2308.13305 (2023-08)
Dynamic Residual Classifier for Class Incremental Learning
2603.08426 (2026-03)
Grow, Assess, Compress: Adaptive Backbone Scaling for Memory-Efficient Class Incremental Learning
resnet18_cbam
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2405.19074 (2024-05)
Resurrecting Old Classes with New Data for Exemplar-Free Continual Learning
resnet18_rep
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2405.19074 (2024-05)
Resurrecting Old Classes with New Data for Exemplar-Free Continual Learning

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

Exemplar-free class-incremental learning using a backbone trained from scratch and starting from a small rst task presents a signicant challenge for continual representation learning. Prototype-based approaches, when continually updated, face the critical issue of semantic drift due to which the old class prototypes drift to dierent positions in the new feature space. Through an analysis of prototype-based continual learning, we show that forgetting is not due to diminished discriminative power of the feature extractor, and can potentially be corrected by drift compensation. To address this, we propose Learnable Drift Compensation (LDC), which can eectively mitigate drift in any moving backbone, whether supervised or unsupervised. LDC is fast and straightforward to integrate on top of existing continual learning approaches. Furthermore, we showcase how LDC can be applied in combination with self-supervised CL methods, resulting in the rst exemplar-free semi-supervised continual learning approach. We achieve state-of-the-art performance in both supervised and semi-supervised settings across multiple datasets. Code is available at https://github.com/alviur/ldc.

For agents

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

get_harvested_code_for_paper("2407.08536")
get_code_for_paper("2407.08536")
have("2407.08536")

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

curl https://syntology.ai/api/ran/2407.08536.json

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

[![Syntology run record](https://syntology.ai/api/ran/2407.08536.svg)](https://syntology.ai/paper/2407.08536)

Connect an agent — have() is free.