SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2308.03374 · ICCV · 2023

Heterogeneous Forgetting Compensation for Class-Incremental Learning

Jiahua Dong, Yang Cong, Gan Sun, Wenqi Liang

arXiv · PDF · Open in the Atlas

Code that ran

10 of 11 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; 1 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 7 failures 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/2308.03374.json · badge: /api/ran/2308.03374.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
JiahuaDong/HFC canonical (classifier label)
classifier basis: census
10 ran · 1 no recorded run
FunctionStatusWhere it lives
build_transform Ran
ran; our contract draft was wrong, not the code
JiahuaDong/HFC/dataset.py
pointer only (licence: NONE) · get_code("cfae7624aaadda21")
How it ran

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

checkpoint_filter_fn Ran
ran; our contract draft was wrong, not the code
JiahuaDong/HFC/vit.py
pointer only (licence: NONE) · get_code("1f65552c7dfe6207")
How it ran

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

get_class_order Ran
ran, honoured the contract we drafted
JiahuaDong/HFC/dataset.py
pointer only (licence: NONE) · get_code("b7350611f8e37d00")
How it ran

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

get_init_weights_vit Ran
ran; our contract draft was wrong, not the code
JiahuaDong/HFC/vit.py
pointer only (licence: NONE); the stored copy get_code serves, from skyofbeginning/fedmgp, is pointer only (licence: NONE) · get_code("6c600a2f0f2361f1")
How it ran

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

get_sampler Ran
ran on a synthesized input
JiahuaDong/HFC/samplers.py
pointer only (licence: NONE) · get_code("c5268f4f4b95766d")
How it ran

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

get_train_sampler Ran
ran on a synthesized input
JiahuaDong/HFC/samplers.py
pointer only (licence: NONE) · get_code("257ab70d9dfb0e64")
How it ran

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

herd_samples Ran
ran; our contract draft was wrong, not the code
JiahuaDong/HFC/rehearsal.py
pointer only (licence: NONE) · get_code("56c8f65df5e769cf")
How it ran

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

icarl_selection Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
JiahuaDong/HFC/rehearsal.py
pointer only (licence: NONE) · get_code("bf7ca0703632a724")
How it ran

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

model_eval Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
JiahuaDong/HFC/utils.py
pointer only (licence: NONE) · get_code("93244ce3ac422ad4")
How it ran

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

resize_pos_embed Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
JiahuaDong/HFC/vit.py
pointer only (licence: NONE) · get_code("321424d80e3f6eed")
How it ran

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

extract_features Not yet run
unverified (harvested, no recorded run)
JiahuaDong/HFC/rehearsal.py
pointer only (licence: NONE) · get_code("c4a2a6fc8d847c56")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, JiahuaDong/HFC 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 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 2 the same month, 2 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
get_init_weights_vit 25 other papers
6 dated earlier, 1 the same month, 17 later, 1 same year, order not determinable · 1 only as an assembly brick
2112.08654 (2021-12)
Learning to Prompt for Continual Learning
2207.12819 (2022-07)
S-Prompts Learning with Pre-trained Transformers: An Occam's Razor for Domain Incremental Learning
2210.08823 (2022-10)
Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning
and 22 more not named here
resize_pos_embed 3 other papers
1 dated earlier, 1 the same month, 1 later
2303.11403 (2023-03)
eP-ALM: Efficient Perceptual Augmentation of Language Models
2308.09610 (2023-08)
On the Effectiveness of LayerNorm Tuning for Continual Learning in Vision Transformers
2311.12048 (2023-11)
One Size Fits All for Semantic Shifts: Adaptive Prompt Tuning for Continual Learning
checkpoint_filter_fn 1 other paper
1 dated earlier
2303.11403 (2023-03)
eP-ALM: Efficient Perceptual Augmentation of Language Models
icarl_selection 1 other paper
1 dated earlier
2204.08932 (2022-04)
Learning to Imagine: Diversify Memory for Incremental Learning using Unlabeled Data

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) has achieved remarkable successes in learning new classes consecutively while overcoming catastrophic forgetting on old categories. However, most existing CIL methods unreasonably assume that all old categories have the same forgetting pace, and neglect negative influence of forgetting heterogeneity among different old classes on forgetting compensation. To surmount the above challenges, we develop a novel Heterogeneous Forgetting Compensation (HFC) model, which can resolve heterogeneous forgetting of easy-to-forget and hard-to-forget old categories from both representation and gradient aspects. Specifically, we design a task-semantic aggregation block to alleviate heterogeneous forgetting from representation aspect. It aggregates local category information within each task to learn task-shared global representations. Moreover, we develop two novel plug-and-play losses: a gradient-balanced forgetting compensation loss and a gradient-balanced relation distillation loss to alleviate forgetting from gradient aspect. They consider gradientbalanced compensation to rectify forgetting heterogeneity of old categories and heterogeneous relation consistency. Experiments on several representative datasets illustrate effectiveness of our HFC model. The code is available at https://github.com/JiahuaDong/HFC.

For agents

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

get_harvested_code_for_paper("2308.03374")
get_code_for_paper("2308.03374")
have("2308.03374")

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

curl https://syntology.ai/api/ran/2308.03374.json

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

[![Syntology run record](https://syntology.ai/api/ran/2308.03374.svg)](https://syntology.ai/paper/2308.03374)

Connect an agent — have() is free.