Papers › Mugs: A Multi-Granular Self-Supervised Learning Framework

Mugs: A Multi-Granular Self-Supervised Learning Framework

27 Mar 2022arXiv:2203.14415archive 2025-07-28

Pan Zhou, Yichen Zhou, Chenyang Si, Weihao Yu, Teck Khim Ng, Shuicheng Yan

In self-supervised learning, multi-granular features are heavily desired though rarely investigated, as different downstream tasks (e.g., general and fine-grained classification) often require different or multi-granular features, e.g. fine- or coarse-grained one or their mixture. In this work, for the first time, we propose an effective MUlti-Granular Self-supervised learning (Mugs) framework to explicitly learn multi-granular visual features. Mugs has three complementary granular supervisions: 1) an instance discrimination supervision (IDS), 2) a novel local-group discrimination supervision (LGDS), and 3) a group discrimination supervision (GDS). IDS distinguishes different instances to learn instance-level fine-grained features. LGDS aggregates features of an image and its neighbors into a local-group feature, and pulls local-group features from different crops of the same image together and push them away for others. It provides complementary instance supervision to IDS via an extra alignment on local neighbors, and scatters different local-groups separately to increase discriminability. Accordingly, it helps learn high-level fine-grained features at a local-group level. Finally, to prevent similar local-groups from being scattered randomly or far away, GDS brings similar samples close and thus pulls similar local-groups together, capturing coarse-grained features at a (semantic) group level. Consequently, Mugs can capture three granular features that often enjoy higher generality on diverse downstream tasks over single-granular features, e.g. instance-level fine-grained features in contrastive learning. By only pretraining on ImageNet-1K, Mugs sets new SoTA linear probing accuracy 82.1% on ImageNet-1K and improves previous SoTA by 1.1%. It also surpasses SoTAs on other tasks, e.g. transfer learning, detection and segmentation.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 21 code samples harvested from 1 repository linked to this paper: 19 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 1 violated, 14 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 21 samples from 1 repository, 19 ran (16 with no instrument failure; 3 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-24 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

sail-sg/mugs officialmentioned on GitHubpytorchApache-2.0Syntology: 21 samples, 19 ran (3 instrument-failed) · 2 unverified 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

21 samples harvested: 19 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 1 violated, 14 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · violated contract
3ran · our draft was wrong
14ran
2unverified

Licence: 3 of the 21 samples are pointer only, meaning Syntology does not serve that copy's text. For 3 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from sail-sg/mugs. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

sail-sg/mugs official repository 21 samples, 19 ran (3 instrument-failed) · 2 unverified
bool_flag in 47 papers utils.py ran · violated contract Apache-2.0 (permissive) here; the stored copy is pointer only · c19231378e41dc5a · report fixture: signature s:str/0/str · returned bool · level recorded 2026-09-24
build_dataset in 151 papers eval/eval_finetuning/eval_finetuning.py ran Apache-2.0 (permissive) · 961c92c8136b0f58 · report fixture: signature is_train:bool/0/bool, args:Args/0/? · returned tuple · level recorded 2026-09-24
build_transform in 170 papers eval/eval_finetuning/eval_finetuning.py ran Apache-2.0 (permissive) · 2c33c9d3e647cbf1 · report fixture: signature is_train:bool/0/bool, args:Args/0/? · returned Compose · level recorded 2026-09-24
clip_gradients in 31 papers src/optimizer.py ran Apache-2.0 (permissive) · 3adab9891c1273b6 · report fixture: signature model:callable/0/?, clip:float/0/float · returned list · level recorded 2026-09-24
cosine_scheduler in 74 papers src/optimizer.py ran Apache-2.0 (permissive) · 990ca4fb0109bfab · report fixture: signature base_value:float/0/float, final_value:float/0/float, epochs:int/0/int, niter_per_ep:int/0/int, warmup_epochs:int/0/int, start_warmup_value:float/0/float · returned ndarray · level recorded 2026-09-24
drop_path in 325 papers
census: 27 implementations from 61 papers, 5 distinct outputs across 2 buckets, one shared input per bucket
src/vision_transformer.py ran Apache-2.0 (permissive) · 793f2b6524ba26f0 · report fixture: signature x:Tensor/4/float, drop_prob:float/0/float, training:bool/0/bool · returned Tensor · level recorded 2026-09-24
find_classes in 61 papers src/dataset.py ran Apache-2.0 (permissive) · e8a374d2601aaaa9 · report fixture: signature directory:str/0/str, class_num:int/0/int · returned tuple · level recorded 2026-09-24
get_logger in 383 papers utils.py ran Apache-2.0 (permissive) · 67bc6a24e6bba540 · report fixture: signature file_path_name:str/0/str · returned RootLogger · level recorded 2026-09-24
get_loss_scale_for_deepspeed in 20 papers eval/eval_finetuning/engine_for_finetuning.py ran · honoured contract Apache-2.0 (permissive) here; the stored copy is pointer only · 29416043c7035e7c · report fixture: signature model:callable/0/? · returned float · level recorded 2026-09-25
get_params_groups in 15 papers src/optimizer.py ran Apache-2.0 (permissive) · 7a2ce97fc746d0ce · report fixture: signature model:callable/0/? · returned list · level recorded 2026-09-24
get_sinusoid_encoding_table in 51 papers eval/eval_finetuning/model_for_finetuning.py ran Apache-2.0 (permissive) · a45ecd9b366b453e · report fixture: signature n_position:int/0/int, d_hid:int/0/int, cls:bool/0/bool · returned Tensor · level recorded 2026-09-24
has_batchnorms utils.py ran Apache-2.0 (permissive) · a35723fa2858c406 · report fixture: signature model:callable/0/? · returned bool · level recorded 2026-09-24
has_file_allowed_extension in 38 papers src/dataset.py ran Apache-2.0 (permissive) · 826e35844a00b3a3 · report fixture: signature filename:str/0/str, extensions:tuple/1/str · returned bool · level recorded 2026-09-24
is_image_file in 157 papers src/dataset.py ran Apache-2.0 (permissive) · 75aa69b9b8b80e72 · report fixture: signature filename:str/0/str · returned bool · level recorded 2026-09-24
shear_x in 43 papers src/RandAugment.py ran · our draft was wrong Apache-2.0 (permissive) · e866e1196986f728 · report fixture: signature img:Image/0/?, factor:float/0/float, resample:int/0/int, fillcolor:tuple/1/int · returned Image · level recorded 2026-09-24
shear_y in 37 papers src/RandAugment.py ran · our draft was wrong Apache-2.0 (permissive) · 7b2503c99c9447fb · report fixture: signature img:Image/0/?, factor:float/0/float, resample:int/0/int, fillcolor:tuple/1/int · returned Image · level recorded 2026-09-24
train_class_batch in 17 papers eval/eval_finetuning/engine_for_finetuning.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · c7976ea27edc377a · report fixture: signature model:callable/0/?, samples:Tensor/2/float, target:Tensor/1/int, criterion:callable/0/? · returned tuple · level recorded 2026-09-25
translate_x_rel in 27 papers src/RandAugment.py ran · our draft was wrong Apache-2.0 (permissive) · 323759f906fbb394 · report fixture: signature img:Image/0/?, pct:float/0/float, resample:int/0/int, fillcolor:tuple/1/int · returned Image · level recorded 2026-09-24
trunc_normal_ in 154 papers
census: 37 implementations from 54 papers, 4 distinct outputs on one shared input
src/vision_transformer.py ran Apache-2.0 (permissive) · e6d9582234fb26e6 · report fixture: signature tensor:Tensor/2/float, mean:float/0/float, std:float/0/float, a:float/0/float, b:float/0/float · returned Tensor · level recorded 2026-09-24
concat_all_gather in 141 papers
census: 7 implementations from 7 papers, 2 distinct outputs on one shared input
src/model.py unverified Apache-2.0 (permissive) · 73cecca9f3575f09 · report
vit_tiny in 40 papers src/vision_transformer.py unverified Apache-2.0 (permissive) · f5479cb822d15445 · report

Tasks

Contrastive LearningSelf-Supervised Image ClassificationSelf-Supervised LearningSemantic SegmentationTransfer Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Self-Supervised Image Classification ImageNet Mugs (VIT-L/16) Number of Params 307M #13 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet Mugs (VIT-L/16) Top 1 Accuracy 82.1% #13 of 144 Archive leaderboard report
Self-Supervised Image Classification ImageNet (finetuned) Mugs (ViT-L/16) Number of Params 307M #25 of 65 Archive leaderboard report
Self-Supervised Image Classification ImageNet (finetuned) Mugs (ViT-L/16) Top 1 Accuracy 85.2% #25 of 65 Archive leaderboard report
Self-Supervised Image Classification ImageNet (finetuned) Mugs (ViT-B/16) Number of Params 85M #32 of 65 Archive leaderboard report
Self-Supervised Image Classification ImageNet (finetuned) Mugs (ViT-B/16) Top 1 Accuracy 84.3% #32 of 65 Archive leaderboard report
Self-Supervised Image Classification ImageNet (finetuned) Mugs (ViT-S/16) Number of Params 21M #50 of 65 Archive leaderboard report
Self-Supervised Image Classification ImageNet (finetuned) Mugs (ViT-S/16) Top 1 Accuracy 82.6% #50 of 65 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.

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