SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2603.08426 · 2026

Grow, Assess, Compress: Adaptive Backbone Scaling for Memory-Efficient Class Incremental Learning

Adrian Garcia-Casta, Jon Irureta, Jon Imaz, Aizea Lojo

arXiv · PDF · Open in the Atlas

Code that ran

9 of 20 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 6 have no contract verdict; 3 failures of our instrument; 11 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/2603.08426.json · badge: /api/ran/2603.08426.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
ai-digilab/GRACE community
Papers with Code archive
9 ran · 11 no recorded run
FunctionStatusWhere it lives
BasicBlock Ran
ran on a synthesized input
ai-digilab/GRACE/models/grace.py
pointer only (licence: NOASSERTION) · get_code("7fc954e2b9931ce9")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ai-digilab/GRACE (NOASSERTION). 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
ai-digilab/GRACE/models/grace.py
pointer only (licence: NOASSERTION) · get_code("e4499befba9ba859")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ai-digilab/GRACE (NOASSERTION). 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
ai-digilab/GRACE/models/grace.py
pointer only (licence: NOASSERTION) · get_code("ad45cc15cdd87626")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ai-digilab/GRACE (NOASSERTION). 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.

DownsampleA Ran
ran on a synthesized input
ai-digilab/GRACE/models/grace.py
pointer only (licence: NOASSERTION) · get_code("cb0f22f6864eb9b4")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ai-digilab/GRACE (NOASSERTION). 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
ai-digilab/GRACE/models/grace.py
pointer only (licence: NOASSERTION) · get_code("eb038f4ed230f75b")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ai-digilab/GRACE (NOASSERTION). 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.

_KD_loss Ran
ran; our contract draft was wrong, not the code
ai-digilab/GRACE/models/grace.py
pointer only (licence: NOASSERTION) · get_code("13f0712d3b4fc01a")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ai-digilab/GRACE (NOASSERTION). 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.

conv1x1 Ran
ran; our contract draft was wrong, not the code
ai-digilab/GRACE/models/grace.py
pointer only (licence: NOASSERTION) · get_code("e6e73849ebab8e0f")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ai-digilab/GRACE (NOASSERTION). 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.

conv3x3 Ran
ran; our contract draft was wrong, not the code
ai-digilab/GRACE/models/grace.py
pointer only (licence: NOASSERTION) · get_code("0fae381fb2fd54e6")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ai-digilab/GRACE (NOASSERTION). 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.

resnet32 Ran
ran on a synthesized input
ai-digilab/GRACE/models/grace.py
pointer only (licence: NOASSERTION) · get_code("22f47f87baaaf7b7")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ai-digilab/GRACE (NOASSERTION). 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.

BaseLearner Not yet run
unverified (harvested, no recorded run)
ai-digilab/GRACE/models/grace.py
pointer only (licence: NOASSERTION) · get_code("cd16fc835c393fa7")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ai-digilab/GRACE (NOASSERTION). 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.

GRACE Not yet run
unverified (harvested, no recorded run)
ai-digilab/GRACE/models/grace.py
pointer only (licence: NOASSERTION) · get_code("8bd8783d76d0f8e7")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ai-digilab/GRACE (NOASSERTION). 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.

GRACENet Not yet run
unverified (harvested, no recorded run)
ai-digilab/GRACE/models/grace.py
pointer only (licence: NOASSERTION) · get_code("fc0b3982a3de2d2c")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ai-digilab/GRACE (NOASSERTION). 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)
ai-digilab/GRACE/models/grace.py
pointer only (licence: NOASSERTION) · get_code("5279599a544dc0f3")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ai-digilab/GRACE (NOASSERTION). 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.

ResNetBasicblock Not yet run
unverified (harvested, no recorded run)
ai-digilab/GRACE/models/grace.py
pointer only (licence: NOASSERTION) · get_code("d231ac0846bb454f")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ai-digilab/GRACE (NOASSERTION). 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)
ai-digilab/GRACE/models/grace.py
pointer only (licence: NOASSERTION) · get_code("3281ad6634a7bfe8")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ai-digilab/GRACE (NOASSERTION). 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.

erank_saturation Not yet run
unverified (harvested, no recorded run)
ai-digilab/GRACE/models/grace.py
pointer only (licence: NOASSERTION) · get_code("6d192883e3907733")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ai-digilab/GRACE (NOASSERTION). 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)
ai-digilab/GRACE/models/grace.py
pointer only (licence: NOASSERTION) · get_code("e74ab9485d1cb03c")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ai-digilab/GRACE (NOASSERTION). 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 Not yet run
unverified (harvested, no recorded run)
ai-digilab/GRACE/models/grace.py
pointer only (licence: NOASSERTION) · get_code("501529c5a0b98bb9")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ai-digilab/GRACE (NOASSERTION). 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 Not yet run
unverified (harvested, no recorded run)
ai-digilab/GRACE/models/grace.py
pointer only (licence: NOASSERTION) · get_code("fa2023a64907170e")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ai-digilab/GRACE (NOASSERTION). 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 Not yet run
unverified (harvested, no recorded run)
ai-digilab/GRACE/models/grace.py
pointer only (licence: NOASSERTION) · get_code("4b295d51ef0a3662")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, ai-digilab/GRACE (NOASSERTION). 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 20 samples lifted from this paper's linked repositories, 20 carry a function identity and 0 do not. Of the 20 distinct functions with an identity, 13 are also present in other papers whose code we hold (13 with at least one paper dated earlier, 4 the same month, 5 later) and 7 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
conv1x1
brick of this paper's assembly: helper
431 other papers
419 dated earlier, 2 the same month, 9 later, 1 undated · 38 only as an assembly brick
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1506.01186 (2015-06)
Cyclical Learning Rates for Training Neural Networks
1507.05717 (2015-07)
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
and 428 more not named here
conv3x3
brick of this paper's assembly: helper
312 other papers
304 dated earlier, 2 the same month, 5 later, 1 undated · 31 only as an assembly brick
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1507.05717 (2015-07)
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
and 309 more not named here
resnet18
brick of this paper's assembly: helper
95 other papers
91 dated earlier, 1 the same month, 2 later, 1 undated
1805.00907 (2018-05)
Glow: Graph Lowering Compiler Techniques for Neural Networks
1902.08153 (2019-02)
Learned Step Size Quantization
1904.01355 (2019-04)
FCOS: Fully Convolutional One-Stage Object Detection
and 92 more not named here
BasicBlock
brick of this paper's assembly: helper
9 other papers
9 dated earlier · 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
_resnet
brick of this paper's assembly: helper
8 other papers
6 dated earlier, 1 the same month, 1 later
2103.10211 (2021-03)
Space-Time Crop & Attend: Improving Cross-modal Video Representation Learning
2105.03245 (2021-05)
Adaptive Focus for Efficient Video Recognition
2107.02156 (2021-07)
Do Different Tracking Tasks Require Different Appearance Models?
and 5 more not named here
Bottleneck
brick of this paper's assembly: helper
7 other papers
7 dated earlier · 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
5 dated earlier · 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
resnet34
brick of this paper's assembly: helper
5 other papers
5 dated earlier
2006.11132 (2020-06)
Deep Transformation-Invariant Clustering
2104.14575 (2021-04)
Unsupervised Layered Image Decomposition into Object Prototypes
2107.09293 (2021-07)
Audio2Head: Audio-driven One-shot Talking-head Generation with Natural Head Motion
and 2 more not named here
DownsampleA
brick of this paper's assembly: helper
3 other papers
3 dated earlier · 2 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
2407.08536 (2024-07)
Exemplar-free Continual Representation Learning via Learnable Drift Compensation
ResNetBasicblock
brick of this paper's assembly: helper
3 other papers
3 dated earlier · 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
2407.08536 (2024-07)
Exemplar-free Continual Representation Learning via Learnable Drift Compensation
resnet50
brick of this paper's assembly: helper
3 other papers
2 dated earlier, 1 later
2105.03245 (2021-05)
Adaptive Focus for Efficient Video Recognition
2402.01887 (2024-02)
On f -Divergence Principled Domain Adaptation: An Improved Framework
2606.27527 (2026-06)
Large Language Model Teaches Visual Students: Cross-Modality Transfer of Fine-Grained Conceptual Knowledge
resnet32
brick of this paper's assembly: helper
2 other papers
2 dated earlier
2204.04662 (2022-04)
FOSTER: Feature Boosting and Compression for Class-Incremental Learning
2308.13305 (2023-08)
Dynamic Residual Classifier for Class Incremental Learning
CifarResNet
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2204.04662 (2022-04)
FOSTER: Feature Boosting and Compression for Class-Incremental 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

Class Incremental Learning (CIL) poses a fundamental challenge: maintaining a balance between the plasticity required to learn new tasks and the stability needed to prevent catastrophic forgetting. While expansion-based methods effectively mitigate forgetting by adding task-specific parameters, they suffer from uncontrolled architectural growth and memory overhead. In this paper, we propose a novel dynamic scaling framework that adaptively manages model capacity through a cyclic "GRow, Assess, ComprEss" (GRACE) strategy. Crucially, we supplement backbone expansion with a novel saturation assessment phase that evaluates the utilization of the model's capacity. This assessment allows the framework to make informed decisions to either expand the architecture or compress the backbones into a streamlined representation, preventing parameter explosion. Experimental results demonstrate that our approach achieves stateof-the-art performance across multiple CIL benchmarks, while reducing memory footprint by up to a 73% compared to purely expansionist models.

For agents

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

get_harvested_code_for_paper("2603.08426")
get_code_for_paper("2603.08426")
have("2603.08426")

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

curl https://syntology.ai/api/ran/2603.08426.json

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

[![Syntology run record](https://syntology.ai/api/ran/2603.08426.svg)](https://syntology.ai/paper/2603.08426)

Connect an agent — have() is free.