Papers › Towards Sustainable Self-supervised Learning

Towards Sustainable Self-supervised Learning

20 Oct 2022arXiv:2210.11016archive 2025-07-28

ShangHua Gao, Pan Zhou, Ming-Ming Cheng, Shuicheng Yan

Although increasingly training-expensive, most self-supervised learning (SSL) models have repeatedly been trained from scratch but not fully utilized, since only a few SOTAs are employed for downstream tasks. In this work, we explore a sustainable SSL framework with two major challenges: i) learning a stronger new SSL model based on the existing pretrained SSL model, also called as "base" model, in a cost-friendly manner, ii) allowing the training of the new model to be compatible with various base models. We propose a Target-Enhanced Conditional (TEC) scheme which introduces two components to the existing mask-reconstruction based SSL. Firstly, we propose patch-relation enhanced targets which enhances the target given by base model and encourages the new model to learn semantic-relation knowledge from the base model by using incomplete inputs. This hardening and target-enhancing help the new model surpass the base model, since they enforce additional patch relation modeling to handle incomplete input. Secondly, we introduce a conditional adapter that adaptively adjusts new model prediction to align with the target of different base models. Extensive experimental results show that our TEC scheme can accelerate the learning speed, and also improve SOTA SSL base models, e.g., MAE and iBOT, taking an explorative step towards sustainable SSL.

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="2210.11016")

Code

Syntology Ran 6 of 8 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 6 ran with no contract checked.

By repository: official repository: 8 samples from 1 repository, 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.

sail-sg/tec officialmentioned on GitHubpytorch 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

8 samples harvested; 6 ran; 0 honoured the contract we drafted; 2 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.

6ran
2unverified

Licence: 8 of the 8 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 sail-sg/tec. “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.

Attention sail-sg/tec/models/models_tec_vit.py official repository ran · metamorphic tier: deterministic no licence file found · pointer only · bde9fdb88d04b910 · report
Block sail-sg/tec/models/models_tec_vit.py official repository ran · metamorphic tier: deterministic no licence file found · pointer only · 18847b8fadd70db0 · report
FeatureAdaptor sail-sg/tec/models/models_tec_vit.py official repository ran · metamorphic tier: deterministic no licence file found · pointer only · 8db0a24fc6a85720 · report
PatchEmbed sail-sg/tec/models/models_tec_vit.py official repository ran · metamorphic tier: deterministic no licence file found · pointer only · f58e26de5060150d · report
ViTDecoderAtt sail-sg/tec/models/models_tec_vit.py official repository ran · metamorphic tier: deterministic no licence file found · pointer only · 19e9319d6e88e674 · report
ViTDecoderFeature sail-sg/tec/models/models_tec_vit.py official repository ran · metamorphic tier: deterministic no licence file found · pointer only · 6a4f060bf556b84d · report
TECViT sail-sg/tec/models/models_tec_vit.py official repository unverified no licence file found · pointer only · fbf181dd5250dedb · report
get_2d_sincos_pos_embed sail-sg/tec/models/models_tec_vit.py official repository unverified no licence file found · pointer only · 7089e8a76f671a0f · report

Tasks

Object DetectionSelf-Supervised Image ClassificationSelf-Supervised LearningSemantic Segmentation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection COCO minival TEC(VIT-B, Mask-RCNN) box AP 54.6 #54 of 220 Archive leaderboard report
Self-Supervised Image Classification ImageNet (finetuned) TEC_MAE (ViT-L/16, 224) Top 1 Accuracy 86.5% #13 of 65 Archive leaderboard report
Semantic Segmentation ADE20K TEC (Vit-B, Upernet) Validation mIoU 51.0 #104 of 235 Archive leaderboard report
Semantic Segmentation ImageNet-S TEC (ViT-B/16, 224x224, SSL+FT, mmseg) mIoU (test) 62.5 #1 of 20 Archive leaderboard report
Semantic Segmentation ImageNet-S TEC (ViT-B/16, 224x224, SSL+FT, mmseg) mIoU (val) 63.2 #1 of 20 Archive leaderboard report
Semantic Segmentation ImageNet-S TEC (ViT-B/16, 224x224, SSL+FT) mIoU (val) 62.0 #3 of 20 Archive leaderboard report
Semantic Segmentation ImageNet-S TEC (ViT-B/16, 224x224, SSL, mmseg) mIoU (test) 46.0 #13 of 20 Archive leaderboard report
Semantic Segmentation ImageNet-S TEC (ViT-B/16, 224x224, SSL, mmseg) mIoU (val) 46.1 #13 of 20 Archive leaderboard report
Semantic Segmentation ImageNet-S TEC (ViT-B/16, 224x224, SSL) mIoU (val) 42.9 #14 of 20 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

ALIGNAdapterBASEMAE

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