Papers › Refign: Align and Refine for Adaptation of Semantic Segmentation to Adverse Conditions

Refign: Align and Refine for Adaptation of Semantic Segmentation to Adverse Conditions

14 Jul 2022arXiv:2207.06825archive 2025-07-28

David Bruggemann, Christos Sakaridis, Prune Truong, Luc van Gool

Due to the scarcity of dense pixel-level semantic annotations for images recorded in adverse visual conditions, there has been a keen interest in unsupervised domain adaptation (UDA) for the semantic segmentation of such images. UDA adapts models trained on normal conditions to the target adverse-condition domains. Meanwhile, multiple datasets with driving scenes provide corresponding images of the same scenes across multiple conditions, which can serve as a form of weak supervision for domain adaptation. We propose Refign, a generic extension to self-training-based UDA methods which leverages these cross-domain correspondences. Refign consists of two steps: (1) aligning the normal-condition image to the corresponding adverse-condition image using an uncertainty-aware dense matching network, and (2) refining the adverse prediction with the normal prediction using an adaptive label correction mechanism. We design custom modules to streamline both steps and set the new state of the art for domain-adaptive semantic segmentation on several adverse-condition benchmarks, including ACDC and Dark Zurich. The approach introduces no extra training parameters, minimal computational overhead -- during training only -- and can be used as a drop-in extension to improve any given self-training-based UDA method. Code is available at https://github.com/brdav/refign.

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="2207.06825")

Code

Syntology Ran 0 of 7 code samples harvested from 1 repository linked to this paper; 7 have no recorded run.

By repository: official repository: 7 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

brdav/refign officialmentioned in papermentioned on GitHubpytorchMIT 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

7 samples harvested; 0 ran; 0 honoured the contract we drafted; 7 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.

7unverified

Licence: 0 of the 7 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 brdav/refign. “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.

extract_crop brdav/refign/models/hrda.py official repository unverified MIT (permissive) · 76d1ac3bd72fbdf4 · report
get_image_size brdav/refign/data_modules/transforms.py official repository unverified MIT (permissive) · 00a098bec6ba382a · report
get_sample_device brdav/refign/data_modules/transforms.py official repository unverified MIT (permissive) · c31ecfad858529ae · report
hr_crop_slice brdav/refign/models/hrda.py official repository unverified MIT (permissive) · b9020407fde39354 · report
imresize brdav/refign/data_modules/transforms.py official repository unverified MIT (permissive) · 829786bd057fa44a · report
my_collate brdav/refign/data_modules/combined_data_module.py official repository unverified MIT (permissive) · 1887a014f4ec6972 · report
scale_box brdav/refign/models/hrda.py official repository unverified MIT (permissive) · 375f71147679dcb7 · report

Tasks

Domain AdaptationSemantic SegmentationUnsupervised Domain Adaptation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Domain Adaptation Cityscapes to ACDC Refign (HRDA) mIoU 72.1 #4 of 16 Archive leaderboard report
Domain Adaptation Cityscapes to ACDC Refign (DAFormer) mIoU 65.5 #8 of 16 Archive leaderboard report
Semantic Segmentation Dark Zurich Refign (HRDA) mIoU 63.9 #1 of 14 Archive leaderboard report
Semantic Segmentation Dark Zurich Refign (DAFormer) mIoU 56.2 #4 of 14 Archive leaderboard report
Semantic Segmentation Nighttime Driving Refign (HRDA) mIoU 58.0 #3 of 13 Archive leaderboard report
Semantic Segmentation Nighttime Driving Refign (DAFormer) mIoU 56.8 #4 of 13 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