Papers › Online Domain Adaptation for Semantic Segmentation in Ever-Changing Conditions

Online Domain Adaptation for Semantic Segmentation in Ever-Changing Conditions

21 Jul 2022arXiv:2207.10667archive 2025-07-28

Theodoros Panagiotakopoulos, Pier Luigi Dovesi, Linus Härenstam-Nielsen, Matteo Poggi

Unsupervised Domain Adaptation (UDA) aims at reducing the domain gap between training and testing data and is, in most cases, carried out in offline manner. However, domain changes may occur continuously and unpredictably during deployment (e.g. sudden weather changes). In such conditions, deep neural networks witness dramatic drops in accuracy and offline adaptation may not be enough to contrast it. In this paper, we tackle Online Domain Adaptation (OnDA) for semantic segmentation. We design a pipeline that is robust to continuous domain shifts, either gradual or sudden, and we evaluate it in the case of rainy and foggy scenarios. Our experiments show that our framework can effectively adapt to new domains during deployment, while not being affected by catastrophic forgetting of the previous domains.

PaperPDFCodeCode 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 21 code samples: 20 from 1 repository linked to this paper, 1 identical to code harvested from another paper's repository. Across all 21: 16 ran (of which 5 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 1 violated, 5 with no contract checked; 7 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 5 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 20 samples from 1 repository, 15 ran (9 with no instrument failure; 6 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. 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. 1 of the 16 samples that ran has no recorded date.

theo2021/onda officialmentioned in papermentioned on GitHubpytorchGPL-2.0Syntology: 20 samples, 15 ran (6 instrument-failed) · 5 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: 16 ran (of which 5 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 1 violated, 5 with no contract checked; 7 where Syntology's instrument failed) · 5 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.

3ran · honoured contract
1ran · violated contract
2ran · our draft was wrong
5ran; the contract check could not run
5ran
5unverified

Licence: 21 of the 21 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 theo2021/onda. 1 sample is listed last, in a group without a repository. “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.

theo2021/onda official repository 20 samples, 15 ran (6 instrument-failed) · 5 unverified
CXE framework/domain_adaptation/methods/prototypes.py ran · honoured contract fingerprinted GPL-2.0 (copyleft) · pointer only · 89efb7f6fd0f5c48 · report fixture: signature predicted:Tensor/2/float, target:Tensor/2/float · returned Tensor · level recorded 2026-09-22
ECE framework/domain_adaptation/methods/prototypes.py ran GPL-2.0 (copyleft) · pointer only · 0bc9611aa0b77309 · report fixture: returned ECE · level recorded 2026-09-22
Monitor framework/domain_adaptation/methods/prototypes.py ran GPL-2.0 (copyleft) · pointer only · a1504096c1d68b2c · report fixture: returned Monitor · level recorded 2026-09-22
batchnorm_stats framework/domain_adaptation/methods/prototypes.py ran GPL-2.0 (copyleft) · pointer only · 7520170a6b8d23cf · report fixture: returned batchnorm_stats · level recorded 2026-09-22
cross_entropy_2d framework/domain_adaptation/methods/prototypes.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted GPL-2.0 (copyleft) · pointer only · c9ad30dd0a145395 · report fixture: signature predict:Tensor/4/float, target:Tensor/3/int, soft:bool/0/bool · returned Tensor · level recorded 2026-09-22
da_model framework/domain_adaptation/methods/prototypes.py ran GPL-2.0 (copyleft) · pointer only · 9fbf4a731ce117c1 · report fixture: returned da_model · level recorded 2026-09-22
entropy_loss in 42 papers
census: 5 implementations from 5 papers, 2 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 2 of 2, arg 1: rank 4, kind float, dtype float32
framework/domain_adaptation/methods/prototypes.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted GPL-2.0 (copyleft) · pointer only · d26c4d52f259e495 · report fixture: signature v:Tensor/4/float · returned Tensor · level recorded 2026-09-22
ewc_loss framework/domain_adaptation/methods/prototypes.py ran · honoured contract GPL-2.0 (copyleft) · pointer only · bfbaedc6197ef57d · report fixture: signature lamda:float/0/float, prev_opt_thetas:list/1/Tensor, cur_thetas:list/1/Tensor, fishers:list/1/Tensor · returned Tensor · level recorded 2026-09-22
loss_calc framework/domain_adaptation/methods/prototypes.py ran · our draft was wrong GPL-2.0 (copyleft) · pointer only · b3ac95de398fe423 · report fixture: signature pred:Tensor/4/float, label:Tensor/3/int, device:device/0/?, soft:bool/0/bool · returned Tensor · level recorded 2026-09-22
lr_poly in 25 papers framework/domain_adaptation/methods/prototypes.py ran · honoured contract fingerprinted GPL-2.0 (copyleft) · pointer only · 9fec89dab050cb13 · report fixture: signature base_lr:float/0/float, iter:int/0/int, max_iter:int/0/int, power:float/0/float · returned float · level recorded 2026-09-22
per_class_iu in 9 papers framework/domain_adaptation/methods/prototypes.py ran · violated contract fingerprinted GPL-2.0 (copyleft) · pointer only · da79e98c38ae72a6 · report fixture: signature hist:ndarray/2/float · returned ndarray · level recorded 2026-09-22
prototype_handler framework/domain_adaptation/methods/prototypes.py ran GPL-2.0 (copyleft) · pointer only · 81c39eaf167b7b81 · report fixture: returned prototype_handler · level recorded 2026-09-22
rce framework/domain_adaptation/methods/prototypes.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant GPL-2.0 (copyleft) · pointer only · 44561849fbfaa903 · report fixture: signature pred:Tensor/4/float, labels:Tensor/3/int, device:device/0/?, soft:bool/0/bool · returned Tensor · level recorded 2026-09-22
regular_loss framework/domain_adaptation/methods/prototypes.py ran; the contract check could not run (RAISES) fingerprinted GPL-2.0 (copyleft) · pointer only · 55c7d29661829cb7 · report fixture: signature regularizer:str/0/str, activation:Tensor/4/float · returned Tensor · level recorded 2026-09-22
segment_sample framework/domain_adaptation/methods/prototypes.py ran · our draft was wrong GPL-2.0 (copyleft) · pointer only · 50b2d3809db27547 · report fixture: signature model:callable/0/?, sample:Tensor/3/float, interp:callable/0/?, label:Tensor/2/int, cfg:DummyConfig/0/?, caption:str/0/str · returned Image · level recorded 2026-09-22
evaluation in 57 papers framework/domain_adaptation/methods/prototypes.py unverified GPL-2.0 (copyleft) · pointer only · cf0328586e1295aa · report
js_divergance framework/domain_adaptation/methods/prototypes.py unverified GPL-2.0 (copyleft) · pointer only · 910de18a01677f86 · report
online_proDA framework/domain_adaptation/methods/prototypes.py unverified GPL-2.0 (copyleft) · pointer only · b36795d53ff302c4 · report
switch_batch_statistics framework/domain_adaptation/methods/prototypes.py unverified GPL-2.0 (copyleft) · pointer only · 978f9f452b9e0145 · report
wandb_image framework/domain_adaptation/methods/prototypes.py unverified GPL-2.0 (copyleft) · pointer only · c2fa9c2db9a59354 · report
Repository not located 1 sample, 1 ran (1 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
fast_hist in 24 papers
census: 2 implementations from 6 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 1, kind int, dtype int32 · arg 2: rank 1, kind int, dtype int32
repository not located ran; the contract check could not run (RAISES) · metamorphic tier: invariant licence of this copy not recorded · d86fb168246b16a4 · report fixture: signature a:ndarray/1/int, b:ndarray/1/int, n:int/0/int · returned ndarray · level recorded, date not recorded

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 Online Domain Adaptation pipeline (graph method: Online Domain Adaptation pipeline). 21 bricks; individually on a fixture: 16 ran (of which 5 constructed an object rather than computing a result; 9 with no instrument failure: 3 honoured, 1 violated, 5 with no contract checked; 7 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

  1. online_proDA entry · level 0 · unverified · b36795d53ff302c4
  2. ECE helper · level 1 · ran · 0bc9611aa0b77309
  3. Monitor helper · level 1 · ran · a1504096c1d68b2c
  4. da_model helper · level 1 · ran · 9fbf4a731ce117c1
  5. evaluation helper · level 0 · unverified · cf0328586e1295aa
  6. ewc_loss helper · level 1 · ran · honoured contract · bfbaedc6197ef57d
  7. js_divergance helper · level 0 · unverified · 910de18a01677f86
  8. loss_calc helper · level 1 · ran · our draft was wrong · b3ac95de398fe423
  9. prototype_handler helper · level 1 · ran · 81c39eaf167b7b81
  10. rce helper · level 1 · ran; the contract check could not run (RAISES) · 44561849fbfaa903
  11. regular_loss loss · level 1 · ran; the contract check could not run (RAISES) · 55c7d29661829cb7
  12. switch_batch_statistics helper · level 0 · unverified · 978f9f452b9e0145
  13. batchnorm_stats helper · level 1 · ran · 7520170a6b8d23cf
  14. fast_hist helper · level 1 · ran; the contract check could not run (RAISES) · d86fb168246b16a4
  15. lr_poly helper · level 1 · ran · honoured contract · 9fec89dab050cb13
  16. per_class_iu helper · level 1 · ran · violated contract · da79e98c38ae72a6
  17. segment_sample helper · level 1 · ran · our draft was wrong · 50b2d3809db27547
  18. entropy_loss helper · level 1 · ran; the contract check could not run (RAISES) · d26c4d52f259e495
  19. cross_entropy_2d helper · level 1 · ran; the contract check could not run (RAISES) · c9ad30dd0a145395
  20. wandb_image helper · level 0 · unverified · c2fa9c2db9a59354
  21. CXE helper · level 1 · ran · honoured contract · 89efb7f6fd0f5c48

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="2207.10667") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Domain AdaptationOnline Domain AdaptationSemantic SegmentationUnsupervised Domain Adaptation

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