Papers › Panoptic Segmentation of Satellite Image Time Series with Convolutional Temporal...

Panoptic Segmentation of Satellite Image Time Series with Convolutional Temporal Attention Networks

16 Jul 2021ICCV 2021 10arXiv:2107.07933archive 2025-07-28

Vivien Sainte Fare Garnot, Loic Landrieu

Unprecedented access to multi-temporal satellite imagery has opened new perspectives for a variety of Earth observation tasks. Among them, pixel-precise panoptic segmentation of agricultural parcels has major economic and environmental implications. While researchers have explored this problem for single images, we argue that the complex temporal patterns of crop phenology are better addressed with temporal sequences of images. In this paper, we present the first end-to-end, single-stage method for panoptic segmentation of Satellite Image Time Series (SITS). This module can be combined with our novel image sequence encoding network which relies on temporal self-attention to extract rich and adaptive multi-scale spatio-temporal features. We also introduce PASTIS, the first open-access SITS dataset with panoptic annotations. We demonstrate the superiority of our encoder for semantic segmentation against multiple competing architectures, and set up the first state-of-the-art of panoptic segmentation of SITS. Our implementation and PASTIS are publicly available.

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 11 code samples harvested from 1 repository linked to this paper: 10 ran (of which 10 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 10 samples that ran constructed an object rather than computing a result. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 11 samples from 1 repository, 10 ran (10 with no instrument failure; 0 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

VSainteuf/utae-paps officialmentioned in papermentioned on GitHubpytorchSyntology: 11 samples, 10 ran (0 instrument-failed) · 1 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

11 samples harvested: 10 ran (of which 10 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 10 samples that ran constructed an object rather than computing a result. “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.

10ran
1unverified

Licence: 0 of the 11 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 VSainteuf/utae-paps. “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”. For 6 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

VSainteuf/utae-paps official repository 11 samples, 10 ran (0 instrument-failed) · 1 unverified
ConvBlock in 61 papers
census: 8 implementations from 8 papers, 6 distinct outputs across 2 buckets, one shared input per bucket
src/backbones/utae.py ran fingerprinted MIT (permissive) · 45da329fac60ca4d · report fixture: returned ConvBlock · level recorded 2026-09-22
ConvLayer in 26 papers src/backbones/utae.py ran fingerprinted MIT (permissive) · e7e11ee365ea4bce · report fixture: returned ConvLayer · level recorded 2026-09-22
DownConvBlock src/backbones/utae.py ran fingerprinted MIT (permissive) · 4a4104e4258a152b · report fixture: returned DownConvBlock · level recorded 2026-09-22
LTAE2d src/backbones/utae.py ran MIT (permissive) · 0c52a14cf35ab27e · report fixture: returned LTAE2d · level recorded 2026-09-22
MultiHeadAttention in 124 papers
census: 9 implementations from 7 papers, 9 distinct outputs across 3 buckets, one shared input per bucket
src/backbones/utae.py ran MIT (permissive) · 05217b7e7b5d3120 · report fixture: returned MultiHeadAttention · level recorded 2026-09-22
PositionalEncoder in 10 papers src/backbones/utae.py ran fingerprinted MIT (permissive) · de6db552db8d11c4 · report fixture: returned PositionalEncoder · level recorded 2026-09-22
ScaledDotProductAttention in 46 papers src/backbones/utae.py ran MIT (permissive) · 2b213e91591f2da8 · report fixture: returned ScaledDotProductAttention · level recorded 2026-09-22
Temporal_Aggregator src/backbones/utae.py ran fingerprinted MIT (permissive) · 95b9e0afd8ec4312 · report fixture: returned Temporal_Aggregator · level recorded 2026-09-22
TemporallySharedBlock src/backbones/utae.py ran MIT (permissive) · f56238c8ef11a6d5 · report fixture: returned TemporallySharedBlock · level recorded 2026-09-22
UpConvBlock src/backbones/utae.py ran MIT (permissive) · a64d9cde74098274 · report fixture: returned UpConvBlock · level recorded 2026-09-22
UTAE src/backbones/utae.py unverified MIT (permissive) · 8abb5042ed8b7f79 · 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 Convolutional Temporal Attention Networks (graph method: Convolutional Temporal Attention Networks). 11 bricks; individually on a fixture: 10 ran (of which 10 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 10 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

  1. UTAE entry · level 0 · unverified · 8abb5042ed8b7f79
  2. ConvBlock helper · level 1 · ran · 45da329fac60ca4d
  3. DownConvBlock model · level 1 · ran · 4a4104e4258a152b
  4. LTAE2d model · level 1 · ran · 0c52a14cf35ab27e
  5. Temporal_Aggregator model · level 1 · ran · 95b9e0afd8ec4312
  6. UpConvBlock model · level 1 · ran · a64d9cde74098274
  7. ConvLayer helper · level 1 · ran · e7e11ee365ea4bce
  8. TemporallySharedBlock helper · level 1 · ran · f56238c8ef11a6d5
  9. MultiHeadAttention helper · level 1 · ran · 05217b7e7b5d3120
  10. PositionalEncoder helper · level 1 · ran · de6db552db8d11c4
  11. ScaledDotProductAttention helper · level 1 · ran · 2b213e91591f2da8

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="2107.07933") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Cloud RemovalEarth ObservationFlood extent forecastingPanoptic SegmentationSegmentationSemantic SegmentationTemporal SequencesTime SeriesTime Series Analysis

Datasets

Introduced by this paper, per the archive.

PASTIS

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Cloud Removal SEN12MS-CR-TS U-TAE PSNR 27.05 #4 of 7 Archive leaderboard report
Cloud Removal SEN12MS-CR-TS U-TAE RMSE 0.051 #4 of 7 Archive leaderboard report
Cloud Removal SEN12MS-CR-TS U-TAE SAM 11.649 #4 of 7 Archive leaderboard report
Cloud Removal SEN12MS-CR-TS U-TAE SSIM 0.849 #4 of 7 Archive leaderboard report
Flood extent forecasting Global Flood forecasting U-TAE F1 score 0.77 #1 of 5 Archive leaderboard report
Panoptic Segmentation PASTIS U-TAE + PaPs PQ 40.4 #3 of 3 Archive leaderboard report
Panoptic Segmentation PASTIS U-TAE + PaPs RQ 49.2 #3 of 3 Archive leaderboard report
Panoptic Segmentation PASTIS U-TAE + PaPs SQ 81.3 #3 of 3 Archive leaderboard report
Semantic Segmentation PASTIS U-TAE Mean IoU (test) 63.1 #3 of 3 Archive leaderboard report
Semantic Segmentation PASTIS U-TAE Number of Params 1.1M #3 of 3 Archive leaderboard report
Semantic Segmentation PASTIS U-TAE Overall Accuracy 83.2 #3 of 3 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