Papers › Time Does Tell: Self-Supervised Time-Tuning of Dense Image Representations

Time Does Tell: Self-Supervised Time-Tuning of Dense Image Representations

22 Aug 2023ICCV 2023 1arXiv:2308.11796archive 2025-07-28

Mohammadreza Salehi, Efstratios Gavves, Cees G. M. Snoek, Yuki M. Asano

Spatially dense self-supervised learning is a rapidly growing problem domain with promising applications for unsupervised segmentation and pretraining for dense downstream tasks. Despite the abundance of temporal data in the form of videos, this information-rich source has been largely overlooked. Our paper aims to address this gap by proposing a novel approach that incorporates temporal consistency in dense self-supervised learning. While methods designed solely for images face difficulties in achieving even the same performance on videos, our method improves not only the representation quality for videos-but also images. Our approach, which we call time-tuning, starts from image-pretrained models and fine-tunes them with a novel self-supervised temporal-alignment clustering loss on unlabeled videos. This effectively facilitates the transfer of high-level information from videos to image representations. Time-tuning improves the state-of-the-art by 8-10% for unsupervised semantic segmentation on videos and matches it for images. We believe this method paves the way for further self-supervised scaling by leveraging the abundant availability of videos. The implementation can be found here : https://github.com/SMSD75/Timetuning

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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 31 code samples harvested from 1 repository linked to this paper: 19 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 2 honoured, 0 violated, 13 with no contract checked; 4 where Syntology's instrument failed) · 12 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 31 samples from 1 repository, 19 ran (15 with no instrument failure; 4 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 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 19 samples that ran have no recorded date.

smsd75/timetuning officialmentioned in papermentioned on GitHubpytorchNOASSERTIONSyntology: 31 samples, 19 ran (4 instrument-failed) · 12 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

31 samples harvested: 19 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 2 honoured, 0 violated, 13 with no contract checked; 4 where Syntology's instrument failed) · 12 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
2ran · our draft was wrong
2ran; the contract check could not run
13ran
12unverified

Licence: 31 of the 31 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 smsd75/timetuning. “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.

smsd75/timetuning official repository 31 samples, 19 ran (4 instrument-failed) · 12 unverified
bfscore bfscore.py ran licence not identified · pointer only · 4a84019b30b6193a · report fixture: signature gt:ndarray/2/int, pr:ndarray/2/int, threshold:float/0/float, verbose:bool/0/bool · returned tuple · level recorded 2026-09-24
bfscore_old bfscore.py ran licence not identified · pointer only · 18c24ad4e75b0f50 · report fixture: signature gtfile:str/0/str, prfile:str/0/str, threshold:int/0/int · returned tuple · level recorded 2026-09-24
build_grid in 15 papers motion_grouping_model.py ran licence not identified · pointer only · a51ebb5e1ba6cf37 · report fixture: signature resolution:list/1/int · returned Tensor · level recorded 2026-09-24
bytescale data_loader.py ran licence not identified · pointer only · 9ce4ded7a45c7696 · report fixture: signature data:ndarray/2/float, cmin:NoneType/0/?, cmax:NoneType/0/?, high:int/0/int, low:int/0/int · returned ndarray · level recorded 2026-09-24
calc_precision_recall in 5 papers bfscore.py ran licence not identified · pointer only · 0801a428f3bdc324 · report fixture: signature contours_a:list/1/list, contours_b:list/1/list, threshold:float/0/float · returned tuple · level recorded 2026-09-24
conv3x3 in 1,376 papers models.py ran · our draft was wrong no licence file found · pointer only · 600ff2c45e0de056 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int, groups:int/0/int, dilation:int/0/int · returned Conv2d · level recorded, date not recorded
cosine_scheduler in 74 papers time_tuning.py ran · honoured contract licence not identified · pointer only · c9ae5a71b1d0c65b · report fixture: signature base_value:float/0/float, final_value:float/0/float, epochs:int/0/int, niter_per_ep:int/0/int · returned ndarray · level recorded 2026-09-22
drop_path in 325 papers
census: 27 implementations from 61 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 2 of 2, arg 1: rank 2, kind float, dtype float32
dino_vision_transformer.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 55120f2026b56aa2 · report fixture: signature x:Tensor/2/float, drop_prob:float/0/float, training:bool/0/bool · returned Tensor · level recorded, date not recorded
get_backbone_prefix leopart.py ran licence not identified · pointer only · f3515400ca858018 · report fixture: signature weights:dict/0/?, arch:str/0/str · returned tuple · level recorded 2026-09-24
get_cluster_precs cluster_based_foreground_extraction.py ran licence not identified · pointer only · 1fcff522c84b8218 · report fixture: signature cluster:Tensor/2/int, mask:Tensor/2/int, k:int/0/int · returned list · level recorded 2026-09-24
pascal_loader leoloader.py ran licence not identified · pointer only · eadb9ed8de52fbc3 · report fixture: signature batch_szie:int/0/int, root:str/0/str, split:str/0/str, val_size:int/0/int, train_size:int/0/int · returned DataLoader · level recorded 2026-09-24
process_attentions models.py ran licence not identified · pointer only · c5e773980206e3b9 · report fixture: signature attentions:Tensor/4/float, spatial_res:int/0/int, threshold:float/0/float, blur_sigma:float/0/float · returned Tensor · level recorded 2026-09-24
process_data_group cluster_based_foreground_extraction.py ran licence not identified · pointer only · 0f2078cd88b80d55 · report fixture: signature data_group:tuple/1/Tensor, scale:int/0/int · returned tuple · level recorded 2026-09-24
resnet18 in 432 papers dul_model.py ran licence not identified · pointer only · 73c9e564019bb977 · report fixture: signature pretrained:str/0/str, remove_layers:list/1/empty, train:bool/0/bool · returned ResNet · level recorded 2026-09-24
restrict_neighborhood in 5 papers time_tuning.py ran · honoured contract fingerprinted licence not identified · pointer only · 3926c0ffeda503f2 · report fixture: signature h:int/0/int, w:int/0/int, size_mask_neighborhood:int/0/int · returned Tensor · level recorded 2026-09-22
sinkhorn in 47 papers
census: 11 implementations from 11 papers, 11 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32
time_tuning.py ran · our draft was wrong fingerprinted licence not identified · pointer only · 0988ed5686f818dc · report fixture: signature Q:Tensor/2/float, nmb_iters:int/0/int, world_size:int/0/int · returned Tensor · level recorded 2026-09-22
spatial_broadcast motion_grouping_model.py ran licence not identified · pointer only · 809d6dcd10040198 · report fixture: signature slots:Tensor/2/float, resolution:tuple/1/int · returned Tensor · level recorded 2026-09-24
spatial_flatten motion_grouping_model.py ran fingerprinted licence not identified · pointer only · b41bb10cde271a7a · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
trunc_normal_ in 154 papers
census: 37 implementations from 54 papers, 4 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
dino_vision_transformer.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only · 915b71e73a54fc97 · 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 2026-09-22
TimeT time_tuning.py unverified licence not identified · pointer only · 9c431c2d7bfe2136 · report
apply_attention_mask time_tuning.py unverified licence not identified · pointer only · f5583623193bd8de · report
apply_attention_mask models.py unverified licence not identified · pointer only · d9fbecd67616025b · report
fromimage data_loader.py unverified licence not identified · pointer only · fa502f356ddd4143 · report
get_backbone_weights leopart.py unverified licence not identified · pointer only · cfe56dffb50d3027 · report
get_model in 368 papers dul_model.py unverified licence not identified · pointer only · 0baae3130bc88bd1 · report
imread in 54 papers data_loader.py unverified licence not identified · pointer only · 36829267cbd7ac1d · report
label_propagation in 6 papers time_tuning.py unverified licence not identified · pointer only · 223126a5c6dbb46b · report
process_attentions time_tuning.py unverified licence not identified · pointer only · aa968da11d21be27 · report
propagate_labels time_tuning.py unverified licence not identified · pointer only · 76f07e9dda6b90e9 · report
proto_clustering clustering.py unverified licence not identified · pointer only · 9b1a2f0da7f00fee · report
vit_tiny in 40 papers dino_vision_transformer.py unverified no licence file found · pointer only · 0a55ce5c7c8fd9fd · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for time-tuning (graph method: time-tuning). 8 bricks; individually on a fixture: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

  1. TimeT entry · level 0 · unverified · 9c431c2d7bfe2136
  2. apply_attention_mask helper · level 0 · unverified · f5583623193bd8de
  3. cosine_scheduler helper · level 1 · ran · honoured contract · c9ae5a71b1d0c65b
  4. propagate_labels helper · level 0 · unverified · 76f07e9dda6b90e9
  5. sinkhorn helper · level 1 · ran · our draft was wrong · 0988ed5686f818dc
  6. process_attentions helper · level 0 · unverified · aa968da11d21be27
  7. label_propagation helper · level 0 · unverified · 223126a5c6dbb46b
  8. restrict_neighborhood helper · level 1 · ran · honoured contract · 3926c0ffeda503f2

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2308.11796") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Self-Supervised LearningSemantic SegmentationUnsupervised Semantic Segmentation

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