Papers › Train Till You Drop: Towards Stable and Robust Source-free Unsupervised 3D Domain Adaptation

Train Till You Drop: Towards Stable and Robust Source-free Unsupervised 3D Domain Adaptation

6 Sep 2024arXiv:2409.04409archive 2025-07-28

Björn Michele, Alexandre Boulch, Tuan-Hung Vu, Gilles Puy, Renaud Marlet, Nicolas Courty

We tackle the challenging problem of source-free unsupervised domain adaptation (SFUDA) for 3D semantic segmentation. It amounts to performing domain adaptation on an unlabeled target domain without any access to source data; the available information is a model trained to achieve good performance on the source domain. A common issue with existing SFUDA approaches is that performance degrades after some training time, which is a by product of an under-constrained and ill-posed problem. We discuss two strategies to alleviate this issue. First, we propose a sensible way to regularize the learning problem. Second, we introduce a novel criterion based on agreement with a reference model. It is used (1) to stop the training when appropriate and (2) as validator to select hyperparameters without any knowledge on the target domain. Our contributions are easy to implement and readily amenable for all SFUDA methods, ensuring stable improvements over all baselines. We validate our findings on various 3D lidar settings, achieving state-of-the-art performance. The project repository (with code) is: github.com/valeoai/TTYD.

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 19 code samples harvested from 1 repository linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 9 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 19 samples from 1 repository, 10 ran (4 with no instrument failure; 6 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 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 10 samples that ran has no recorded date.

valeoai/ttyd officialmentioned in papermentioned on GitHubpytorchSyntology: 19 samples, 10 ran (6 instrument-failed) · 9 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

19 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 9 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
6ran · our draft was wrong
3ran
9unverified

Licence: 19 of the 19 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 valeoai/ttyd. “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.

valeoai/ttyd official repository 19 samples, 10 ran (6 instrument-failed) · 9 unverified
WeightEMA train_ttyd_st.py ran no licence file found · pointer only · d7fe71efd7be18ce · report fixture: returned NoneType · level recorded 2026-09-24
class_mapping_da datasets/Waymo.py ran · our draft was wrong no licence file found · pointer only · 3a4368ddb37954eb · report fixture: signature config:dict/0/? · returned dict · level recorded 2026-09-24
class_mapping_da datasets/nuscenes.py ran · our draft was wrong no licence file found · pointer only · 2aa16d95d3187709 · report fixture: signature config:dict/0/? · returned dict · level recorded 2026-09-24
class_mapping_da datasets/pandaset.py ran · our draft was wrong no licence file found · pointer only · a1a69f062e8f1dcb · report fixture: signature config:dict/0/? · returned dict · level recorded 2026-09-24
count_parameters in 278 papers networks/network.py ran · honoured contract no licence file found · pointer only · f6b944f50d3f15ae · report fixture: signature model:callable/0/? · returned int · level recorded, date not recorded
parse_header in 11 papers datasets/semantic_kitti.py ran no licence file found · pointer only · 27aa4c3bde697bf7 · report fixture: signature plyfile:BytesIO/0/?, ext:str/0/str · returned tuple · level recorded 2026-09-24
parse_mesh_header in 7 papers datasets/semantic_kitti.py ran no licence file found · pointer only · 5f8cf95da4e4af73 · report fixture: signature plyfile:BytesIO/0/?, ext:str/0/str · returned tuple · level recorded 2026-09-24
read_ply in 16 papers datasets/semantic_kitti.py ran · our draft was wrong no licence file found · pointer only · 2dd532d51a1cbc79 · report fixture: signature filename:str/0/str, triangular_mesh:bool/0/bool · returned ndarray · level recorded 2026-09-24
read_yaml_file in 7 papers configs_and_mappings.py ran · our draft was wrong no licence file found · pointer only · 5db569379bf8e3f7 · report fixture: signature file_path:str/0/str · returned dict · level recorded 2026-09-24
update_running_conf train_ttyd_st.py ran · our draft was wrong no licence file found · pointer only · 94ccab2d12942c7b · report fixture: signature probs:Tensor/2/float, running_conf:Tensor/1/float, THRESHOLD_BETA:float/0/float, tolerance:float/0/float · returned Tensor · level recorded 2026-09-24
evel_stu train_ttyd_st.py unverified no licence file found · pointer only · d92d30cd77706228 · report
main in 235 papers train_ttyd_st.py unverified no licence file found · pointer only · 14efea405afb2bd4 · report
main in 235 papers train_ttyd_core.py unverified no licence file found · pointer only · b8410a4af7b88726 · report
make_a_deepcopy train_ttyd_st.py unverified no licence file found · pointer only · f887cfb9d65b5961 · report
pseudo_label train_ttyd_st.py unverified no licence file found · pointer only · 4c1b0ec199898b71 · report
pseudo_label train_ttyd_st.py unverified no licence file found · pointer only · 9b976ce7df83de81 · report
pseudo_labels_probs train_ttyd_st.py unverified no licence file found · pointer only · 5d8d1036a9d3aed2 · report
validation_performance_pseudo_labels train_ttyd_st.py unverified no licence file found · pointer only · 2a033443755430c4 · 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 Train Till You Drop (graph method: Train Till You Drop). 9 bricks; individually on a fixture: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified. The assembly has not been run end-to-end.

  1. main entry · level 0 · unverified · 14efea405afb2bd4
  2. WeightEMA update_rule · level 1 · ran · d7fe71efd7be18ce
  3. entropy loss · level 0 · unverified · a801fbd82ec2a383
  4. evel_stu metric · level 0 · unverified · d92d30cd77706228
  5. make_a_deepcopy helper · level 0 · unverified · f887cfb9d65b5961
  6. pseudo_label helper · level 0 · unverified · 4c1b0ec199898b71
  7. pseudo_labels_probs helper · level 0 · unverified · 5d8d1036a9d3aed2
  8. update_running_conf helper · level 1 · ran · our draft was wrong · 94ccab2d12942c7b
  9. validation_performance_pseudo_labels metric · level 0 · unverified · 2a033443755430c4

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="2409.04409") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

3D Semantic Segmentation3D Source-Free Domain AdaptationDomain AdaptationSemantic SegmentationSource-Free Domain AdaptationUnsupervised Domain Adaptation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Source-Free Domain Adaptation SynLiDAR-to-SemanticKITTI TTYD mIoU 32.4 #1 of 1 Archive leaderboard report
3D Source-Free Domain Adaptation SynLiDAR-to-SemanticPOSS TTYD mIoU 39.1 #1 of 1 Archive leaderboard report
3D Source-Free Domain Adaptation nuScenes-to-Pandaset TTYD mIoU 65.7 #1 of 1 Archive leaderboard report
3D Source-Free Domain Adaptation nuScenes-to-SemanticKITTI TTYD mIoU 45.4 #1 of 1 Archive leaderboard report
3D Source-Free Domain Adaptation nuScenes-to-SemanticPOSS TTYD mIoU 64.5 #1 of 1 Archive leaderboard report
3D Source-Free Domain Adaptation nuScenes-to-Waymo Open Dataset TTYD mIoU 55.5 #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