Papers › Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics...

Taking A Closer Look at Domain Shift: Category-level Adversaries for Semantics Consistent Domain Adaptation

25 Sep 2018CVPR 2019 6arXiv:1809.09478archive 2025-07-28

Yawei Luo, Liang Zheng, Tao Guan, Junqing Yu, Yi Yang

We consider the problem of unsupervised domain adaptation in semantic segmentation. The key in this campaign consists in reducing the domain shift, i.e., enforcing the data distributions of the two domains to be similar. A popular strategy is to align the marginal distribution in the feature space through adversarial learning. However, this global alignment strategy does not consider the local category-level feature distribution. A possible consequence of the global movement is that some categories which are originally well aligned between the source and target may be incorrectly mapped. To address this problem, this paper introduces a category-level adversarial network, aiming to enforce local semantic consistency during the trend of global alignment. Our idea is to take a close look at the category-level data distribution and align each class with an adaptive adversarial loss. Specifically, we reduce the weight of the adversarial loss for category-level aligned features while increasing the adversarial force for those poorly aligned. In this process, we decide how well a feature is category-level aligned between source and target by a co-training approach. In two domain adaptation tasks, i.e., GTA5 -> Cityscapes and SYNTHIA -> Cityscapes, we validate that the proposed method matches the state of the art in segmentation accuracy.

PaperPDFConference PDFCodeCode 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="1809.09478")

Code

Syntology Ran 8 of 14 code samples harvested from 1 repository linked to this paper; 6 have no recorded run. Of those that ran: 4 ran · honoured contract; 1 ran · violated contract; 1 ran · our draft was wrong; 2 ran · fixture could not drive it.

By repository: official repository: 14 samples from 1 repository, 8 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

RoyalVane/CLAN officialmentioned in paperpytorchMIT 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

14 samples harvested; 8 ran; 4 honoured the contract we drafted; 6 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.

4ran · honoured contract
1ran · violated contract
1ran · our draft was wrong
2ran · fixture could not drive it
6unverified

Licence: 0 of the 14 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 RoyalVane/CLAN. “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.

colorize_mask RoyalVane/CLAN/CLAN_evaluate.py official repository ran · honoured contract MIT (permissive) · 21ac171a17099011 · report
conv3x3 RoyalVane/CLAN/model/CLAN_G.py official repository ran · our draft was wrong MIT (permissive) · fac5364e2f53c6db · report
create_map RoyalVane/CLAN/CLAN_evaluate_bulk.py official repository ran · fixture could not drive it MIT (permissive) · 844cbbd42f58aa56 · report
fast_hist RoyalVane/CLAN/CLAN_iou.py official repository ran · fixture could not drive it MIT (permissive) · d86fb168246b16a4 · report
lr_poly RoyalVane/CLAN/CLAN_train.py official repository ran · honoured contract fingerprinted MIT (permissive) · b3b7c1c716f4ca66 · report
lr_warmup RoyalVane/CLAN/CLAN_train.py official repository ran · honoured contract fingerprinted MIT (permissive) · 668bc14a07c5d7ac · report
outS RoyalVane/CLAN/model/CLAN_G.py official repository ran · honoured contract fingerprinted MIT (permissive) · 27504cbeb5811ea6 · report
per_class_iu RoyalVane/CLAN/CLAN_iou.py official repository ran · violated contract fingerprinted MIT (permissive) · b1c59751f8968e99 · report
Res_Deeplab RoyalVane/CLAN/model/CLAN_G.py official repository unverified MIT (permissive) · b76ad4293318958f · report
channel_1toN RoyalVane/CLAN/utils/loss.py official repository unverified MIT (permissive) · f6bba73be87e302f · report
label_mapping RoyalVane/CLAN/CLAN_iou.py official repository unverified MIT (permissive) · bcfd47261d90f53e · report
onedim_superpixel2im RoyalVane/CLAN/utils/visual.py official repository unverified MIT (permissive) · 839955eed0744a55 · report
onedim_tensor2im RoyalVane/CLAN/utils/visual.py official repository unverified MIT (permissive) · c393ac985b152f6b · report
tensor2im RoyalVane/CLAN/utils/visual.py official repository unverified MIT (permissive) · 1cc896f07ee44bf0 · report

Tasks

Domain AdaptationSemantic SegmentationSynthetic-to-Real TranslationUnsupervised Domain Adaptation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic Segmentation DADA-seg CLAN mIoU 28.76 #8 of 28 Archive leaderboard report
Semantic Segmentation DensePASS CLAN mIoU 31.46% #25 of 36 Archive leaderboard report
Synthetic-to-Real Translation GTAV-to-Cityscapes Labels CLAN mIoU 43.2 #63 of 73 Archive leaderboard report
Synthetic-to-Real Translation SYNTHIA-to-Cityscapes CLAN MIoU (13 classes) 47.8 #37 of 38 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