Papers › Hyperbolic Active Learning for Semantic Segmentation under Domain Shift

Hyperbolic Active Learning for Semantic Segmentation under Domain Shift

19 Jun 2023arXiv:2306.11180archive 2025-07-28

Luca Franco, Paolo Mandica, Konstantinos Kallidromitis, Devin Guillory, Yu-Teng Li, Trevor Darrell, Fabio Galasso

We introduce a hyperbolic neural network approach to pixel-level active learning for semantic segmentation. Analysis of the data statistics leads to a novel interpretation of the hyperbolic radius as an indicator of data scarcity. In HALO (Hyperbolic Active Learning Optimization), for the first time, we propose the use of epistemic uncertainty as a data acquisition strategy, following the intuition of selecting data points that are the least known. The hyperbolic radius, complemented by the widely-adopted prediction entropy, effectively approximates epistemic uncertainty. We perform extensive experimental analysis based on two established synthetic-to-real benchmarks, i.e. GTAV → Cityscapes and SYNTHIA → Cityscapes. Additionally, we test HALO on Cityscape → ACDC for domain adaptation under adverse weather conditions, and we benchmark both convolutional and attention-based backbones. HALO sets a new state-of-the-art in active learning for semantic segmentation under domain shift and it is the first active learning approach that surpasses the performance of supervised domain adaptation while using only a small portion of labels (i.e., 1%).

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="2306.11180")

Code

Syntology Ran 3 of 8 code samples harvested from 1 repository linked to this paper; 5 have no recorded run. Of those that ran: 2 ran · honoured contract; 1 ran · our draft was wrong.

By repository: official repository: 8 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

paolomandica/HALO officialmentioned in papermentioned on GitHubpytorch 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

8 samples harvested; 3 ran; 2 honoured the contract we drafted; 5 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.

2ran · honoured contract
1ran · our draft was wrong
5unverified

Licence: 0 of the 8 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 paolomandica/HALO. “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.

normalize_map paolomandica/HALO/core/active/build.py official repository ran · honoured contract fingerprinted MIT (permissive) · 3ae23f8e61562cc3 · report
select_pixels_to_label paolomandica/HALO/core/active/build.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 86d1926012f68faa · report
to_np_array paolomandica/HALO/core/active/build.py official repository ran · honoured contract fingerprinted MIT (permissive) · fec2f2f8d93d1fa8 · report
FloatingRegionScore paolomandica/HALO/core/active/build.py official repository unverified MIT (permissive) · eab1d6b272518010 · report
HyperMapper paolomandica/HALO/core/active/build.py official repository unverified MIT (permissive) · 3e033d4c609ee08a · report
RegionSelection paolomandica/HALO/core/active/build.py official repository unverified MIT (permissive) · accfc8d80e6e1e15 · report
init_conv_layer paolomandica/HALO/core/active/build.py official repository unverified MIT (permissive) · 376c19d52db9551b · report
visualization_plots paolomandica/HALO/core/active/build.py official repository unverified MIT (permissive) · 55135699ac9f4cd8 · report

Tasks

Domain AdaptationSemantic SegmentationSource-Free Domain Adaptation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Domain Adaptation Cityscapes to ACDC HALO mIoU 71.9 #5 of 16 Archive leaderboard report
Domain Adaptation GTA5 to Cityscapes HALO mIoU 77.8 #1 of 28 Archive leaderboard report
Domain Adaptation SYNTHIA-to-Cityscapes HALO Extra Manual Annotation Yes #1 of 33 Archive leaderboard report
Domain Adaptation SYNTHIA-to-Cityscapes HALO mIoU 78.1 #1 of 33 Archive leaderboard report
Semantic Segmentation Cityscapes val HALO mIoU 77.8 #64 of 99 Archive leaderboard report
Source-Free Domain Adaptation GTA5 to Cityscapes HALO mIoU 73.3 #1 of 1 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