Papers › Continual Learning: Forget-free Winning Subnetworks for Video Representations

Continual Learning: Forget-free Winning Subnetworks for Video Representations

19 Dec 2023arXiv:2312.11973archive 2025-07-28

Haeyong Kang, Jaehong Yoon, Sung Ju Hwang, Chang D. Yoo

Inspired by the Lottery Ticket Hypothesis (LTH), which highlights the existence of efficient subnetworks within larger, dense networks, a high-performing Winning Subnetwork (WSN) in terms of task performance under appropriate sparsity conditions is considered for various continual learning tasks. It leverages pre-existing weights from dense networks to achieve efficient learning in Task Incremental Learning (TIL) and Task-agnostic Incremental Learning (TaIL) scenarios. In Few-Shot Class Incremental Learning (FSCIL), a variation of WSN referred to as the Soft subnetwork (SoftNet) is designed to prevent overfitting when the data samples are scarce. Furthermore, the sparse reuse of WSN weights is considered for Video Incremental Learning (VIL). The use of Fourier Subneural Operator (FSO) within WSN is considered. It enables compact encoding of videos and identifies reusable subnetworks across varying bandwidths. We have integrated FSO into different architectural frameworks for continual learning, including VIL, TIL, and FSCIL. Our comprehensive experiments demonstrate FSO's effectiveness, significantly improving task performance at various convolutional representational levels. Specifically, FSO enhances higher-layer performance in TIL and FSCIL and lower-layer performance in VIL.

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="2312.11973")

Code

Syntology Ran 7 of 15 code samples harvested from 2 repositories linked to this paper; 8 have no recorded run. Of those that ran: 1 ran · honoured contract; 5 ran · our draft was wrong; 1 ran · fixture could not drive it.

By repository: official repository: 3 samples from 1 repository, 2 ran; community (archive-listed): 12 samples from 1 repository, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

ihaeyong/pfnr officialmentioned in papermentioned on GitHubpytorch report
ihaeyong/pnr mentioned 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

15 samples harvested; 7 ran; 1 honoured the contract we drafted; 8 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.

1ran · honoured contract
5ran · our draft was wrong
1ran · fixture could not drive it
8unverified

Licence: 0 of the 15 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.

get_consolidated_masks ihaeyong/pfnr/train_nerv.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · c24fca3836221111 · report
get_task_sparsity ihaeyong/pfnr/train_nerv.py official repository ran · our draft was wrong MIT (permissive) · 144b98b55047b2da · report
evaluate ihaeyong/pfnr/train_nerv.py official repository unverified MIT (permissive) · d8684b8a9ca3ef7a · report
ActivationLayer ihaeyong/pnr/model_nerv.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 878fd412e7a78234 · report
MLP ihaeyong/pnr/model_nerv.py community (archive-listed) ran · fixture could not drive it MIT (permissive) · 4b4bad794e3e1cab · report
NormLayer ihaeyong/pnr/model_nerv.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 853ab1b19577355a · report
compute_conv_output_size ihaeyong/pnr/model/subnet.py community (archive-listed) ran · honoured contract MIT (permissive) · e71c2a2bc2fc8909 · report
percentile ihaeyong/pnr/model/subnet.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 913e2d426938c7d4 · report
all_gather ihaeyong/pnr/utils.py community (archive-listed) unverified MIT (permissive) · a1ba6b0c4d96716f · report
all_reduce ihaeyong/pnr/utils.py community (archive-listed) unverified MIT (permissive) · 439067335e7b67b5 · report
get_consolidated_masks ihaeyong/pnr/plot_nerv_eval.py community (archive-listed) unverified MIT (permissive) · cc46e27629d64950 · report
get_coused_sparsity ihaeyong/pnr/train_nerv_eval.py community (archive-listed) unverified MIT (permissive) · f0e8e55d92917b22 · report
get_reused_sparsity ihaeyong/pnr/train_nerv_eval.py community (archive-listed) unverified MIT (permissive) · 49fb8932e40b133e · report
get_task_sparsity ihaeyong/pnr/train_nerv_eval.py community (archive-listed) unverified MIT (permissive) · 000804ce4ed442ee · report
quantize_per_tensor ihaeyong/pnr/utils.py community (archive-listed) unverified MIT (permissive) · 9ba78d582d59f8ed · report

Tasks

Class Incremental LearningContinual LearningFew-Shot Class-Incremental LearningIncremental Learningclass-incremental learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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