Papers › MOS: Model Surgery for Pre-Trained Model-Based Class-Incremental Learning

MOS: Model Surgery for Pre-Trained Model-Based Class-Incremental Learning

12 Dec 2024arXiv:2412.09441archive 2025-07-28

Hai-Long Sun, Da-Wei Zhou, Hanbin Zhao, Le Gan, De-Chuan Zhan, Han-Jia Ye

Class-Incremental Learning (CIL) requires models to continually acquire knowledge of new classes without forgetting old ones. Despite Pre-trained Models (PTMs) have shown excellent performance in CIL, catastrophic forgetting still occurs as the model learns new concepts. Existing work seeks to utilize lightweight components to adjust the PTM, while the forgetting phenomenon still comes from {\em parameter and retrieval} levels. Specifically, iterative updates of the model result in parameter drift, while mistakenly retrieving irrelevant modules leads to the mismatch during inference. To this end, we propose MOdel Surgery (MOS) to rescue the model from forgetting previous knowledge. By training task-specific adapters, we continually adjust the PTM to downstream tasks. To mitigate parameter-level forgetting, we present an adapter merging approach to learn task-specific adapters, which aims to bridge the gap between different components while reserve task-specific information. Besides, to address retrieval-level forgetting, we introduce a training-free self-refined adapter retrieval mechanism during inference, which leverages the model's inherent ability for better adapter retrieval. By jointly rectifying the model with those steps, MOS can robustly resist catastrophic forgetting in the learning process. Extensive experiments on seven benchmark datasets validate MOS's state-of-the-art performance. Code is available at: https://github.com/sun-hailong/AAAI25-MOS

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2412.09441")

Code

Syntology Ran 6 of 17 code samples harvested from 2 repositories linked to this paper; 11 have no recorded run. Of those that ran: 2 ran · honoured contract; 3 ran · our draft was wrong; 1 ran · fixture could not drive it.

By repository: official repository: 17 samples from 2 repositories, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

sun-hailong/aaai25-mos officialmentioned in papermentioned on GitHubpytorch report
sun-hailong/lamda-pilot officialmentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

17 samples harvested; 6 ran; 2 honoured the contract we drafted; 11 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · honoured contract
3ran · our draft was wrong
1ran · fixture could not drive it
11unverified

Licence: 12 of the 17 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

conv1x1 sun-hailong/lamda-pilot/backbone/resnet.py official repository ran · our draft was wrong MIT (permissive) · d9def42110729a85 · report
conv3x3 sun-hailong/lamda-pilot/backbone/resnet.py official repository ran · our draft was wrong MIT (permissive) · 160bb14bd76201b4 · report
count_parameters sun-hailong/aaai25-mos/utils/toolkit.py official repository ran · honoured contract no licence file found · pointer only · 6bdbe3d6368c4cde · report
reduce_proxies sun-hailong/aaai25-mos/backbone/linears.py official repository ran · fixture could not drive it fingerprinted no licence file found · pointer only · 4072283c98270784 · report
target2onehot sun-hailong/aaai25-mos/utils/toolkit.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · 284e2e0345abe291 · report
tensor2numpy sun-hailong/aaai25-mos/utils/toolkit.py official repository ran · honoured contract no licence file found · pointer only · 929c76a2fa2e8c42 · report
accimage_loader sun-hailong/aaai25-mos/utils/data_manager.py official repository unverified no licence file found · pointer only · cf462ad7948ff43b · report
build_transform sun-hailong/aaai25-mos/utils/data.py official repository unverified no licence file found · pointer only · b620954495190c1a · report
build_transform_coda_prompt sun-hailong/aaai25-mos/utils/data.py official repository unverified no licence file found · pointer only · 84339af3a90298e2 · report
default_loader sun-hailong/aaai25-mos/utils/data_manager.py official repository unverified no licence file found · pointer only · 2c9953e20558c977 · report
get_backbone sun-hailong/aaai25-mos/utils/inc_net.py official repository unverified no licence file found · pointer only · 1228159f65c11926 · report
interpolate_weights sun-hailong/lamda-pilot/models/cofima.py official repository unverified MIT (permissive) · c4068ef3da0e1260 · report
pil_loader sun-hailong/aaai25-mos/utils/data_manager.py official repository unverified no licence file found · pointer only · 66b63ed4f327a712 · report
regularized_cn sun-hailong/lamda-pilot/models/dgr.py official repository unverified MIT (permissive) · d7c13335c21a1194 · report
resnet18 sun-hailong/lamda-pilot/backbone/resnet.py official repository unverified MIT (permissive) · 1b21828124579725 · report
vit_base_patch16_224_in21k_mos sun-hailong/aaai25-mos/backbone/vit_mos.py official repository unverified no licence file found · pointer only · b29b6be35c316663 · report
vit_base_patch16_224_mos sun-hailong/aaai25-mos/backbone/vit_mos.py official repository unverified no licence file found · pointer only · 2dc78c999d4d5662 · report

Tasks

Class Incremental LearningIncremental LearningRetrievalclass-incremental learningmodel

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Adapter

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections