Papers › Dual-Perspective Knowledge Enrichment for Semi-Supervised 3D Object Detection

Dual-Perspective Knowledge Enrichment for Semi-Supervised 3D Object Detection

10 Jan 2024arXiv:2401.05011archive 2025-07-28

Yucheng Han, Na Zhao, Weiling Chen, Keng Teck Ma, Hanwang Zhang

Semi-supervised 3D object detection is a promising yet under-explored direction to reduce data annotation costs, especially for cluttered indoor scenes. A few prior works, such as SESS and 3DIoUMatch, attempt to solve this task by utilizing a teacher model to generate pseudo-labels for unlabeled samples. However, the availability of unlabeled samples in the 3D domain is relatively limited compared to its 2D counterpart due to the greater effort required to collect 3D data. Moreover, the loose consistency regularization in SESS and restricted pseudo-label selection strategy in 3DIoUMatch lead to either low-quality supervision or a limited amount of pseudo labels. To address these issues, we present a novel Dual-Perspective Knowledge Enrichment approach named DPKE for semi-supervised 3D object detection. Our DPKE enriches the knowledge of limited training data, particularly unlabeled data, from two perspectives: data-perspective and feature-perspective. Specifically, from the data-perspective, we propose a class-probabilistic data augmentation method that augments the input data with additional instances based on the varying distribution of class probabilities. Our DPKE achieves feature-perspective knowledge enrichment by designing a geometry-aware feature matching method that regularizes feature-level similarity between object proposals from the student and teacher models. Extensive experiments on the two benchmark datasets demonstrate that our DPKE achieves superior performance over existing state-of-the-art approaches under various label ratio conditions. The source code will be made available to the public.

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 18 code samples harvested from 1 repository linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 7 where Syntology's instrument failed) · 9 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 18 samples from 1 repository, 9 ran (2 with no instrument failure; 7 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 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

tingxueronghua/dpke officialmentioned in papermentioned on GitHubpytorchSyntology: 18 samples, 9 ran (7 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

18 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 7 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 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.

2ran · honoured contract
5ran · our draft was wrong
2ran; the contract check could not run
9unverified

Licence: 18 of the 18 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 tingxueronghua/dpke. “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.

tingxueronghua/dpke official repository 18 samples, 9 ran (7 instrument-failed) · 9 unverified
flip_axis_to_camera in 12 papers models/loss_helper_unlabeled.py ran · honoured contract fingerprinted no licence file found · pointer only · eddd23cbbb297813 · report fixture: signature pc:ndarray/2/float · returned ndarray · level recorded 2026-09-22
get_3d_box models/loss_helper_unlabeled.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 2d07150ed0255867 · report fixture: signature box_size:ndarray/1/float, heading_angle:float/0/float, center:ndarray/1/float · returned ndarray · level recorded 2026-09-22
huber_loss in 34 papers
census: 6 implementations from 7 papers, 5 distinct outputs across 5 buckets, one shared input per bucket this sample: bucket 1 of 5, arg 1: rank 2, kind float, dtype float32
models/loss_helper_unlabeled.py ran · our draft was wrong fingerprinted no licence file found · pointer only · bd237d8a9c8b33f6 · report fixture: signature error:Tensor/2/float, delta:float/0/float · returned Tensor · level recorded 2026-09-22
lhs_3d_faster_samecls models/loss_helper_unlabeled.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 8524fa3afc82724b · report fixture: signature boxes:ndarray/2/float, overlap_threshold:float/0/float, old_type:bool/0/bool · returned list · level recorded 2026-09-22
nn_distance in 5 papers models/loss_helper_unlabeled.py ran · our draft was wrong no licence file found · pointer only · debfd9f8a49596b7 · report fixture: signature pc1:Tensor/3/float, pc2:Tensor/3/float, l1smooth:bool/0/bool, delta:float/0/float, l1:bool/0/bool · returned tuple · level recorded 2026-09-22
nn_distance_withcls models/loss_helper_unlabeled.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 3c3fa3ae7dd47d03 · report fixture: signature pc1:Tensor/3/float, pc2:Tensor/3/float, cls1:Tensor/2/int, cls2:Tensor/2/int, l1smooth:bool/0/bool, delta:float/0/float, l1:bool/0/bool · returned tuple · level recorded 2026-09-22
roty in 19 papers models/loss_helper_unlabeled.py ran · honoured contract fingerprinted no licence file found · pointer only · e1f78f900f99690f · report fixture: signature t:float/0/float · returned ndarray · level recorded 2026-09-22
trans_angle models/loss_helper_unlabeled.py ran · our draft was wrong no licence file found · pointer only · 5fcf347710b4be86 · report fixture: signature angle_class:Tensor/1/int, angle_residual:Tensor/1/float, flip_x_axis:Tensor/1/bool, flip_y_axis:Tensor/1/bool, rot_angle:Tensor/1/float, config:Config/0/? · returned tuple · level recorded 2026-09-22
trans_size models/loss_helper_unlabeled.py ran · our draft was wrong no licence file found · pointer only · 1411dfea7f7ed8cd · report fixture: returned Tensor · level recorded 2026-09-22
box3d_iou_batch_gpu models/loss_helper_unlabeled.py unverified no licence file found · pointer only · 4e7246c36ad9782e · report
compute_box_and_sem_cls_loss models/loss_helper_unlabeled.py unverified no licence file found · pointer only · 09393aa9e8d8ad6b · report
compute_iou_labels models/loss_helper_unlabeled.py unverified no licence file found · pointer only · 75ff5a97f8ffda97 · report
compute_objectness_gt models/loss_helper_unlabeled.py unverified no licence file found · pointer only · 619751b3a15daea6 · report
compute_objectness_loss models/loss_helper_unlabeled.py unverified no licence file found · pointer only · cd1cc668b7388a0c · report
get_pseudo_detection_loss models/loss_helper_unlabeled.py unverified no licence file found · pointer only · 55394dc469527afa · report
get_pseudo_labels models/loss_helper_unlabeled.py unverified no licence file found · pointer only · 493ce76f06838497 · report
get_unlabeled_loss models/loss_helper_unlabeled.py unverified no licence file found · pointer only · 18ba621d8879d6c7 · report
trans_center models/loss_helper_unlabeled.py unverified no licence file found · pointer only · a3178bc8fc8015c2 · 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 Dual-Perspective Knowledge Enrichment (DPKE) (graph method: Dual-Perspective Knowledge Enrichment (DPKE)). 18 bricks; individually on a fixture: 9 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 7 where Syntology's instrument failed) · 9 unverified. The assembly has not been run end-to-end.

  1. get_unlabeled_loss entry · level 0 · unverified · 18ba621d8879d6c7
  2. get_pseudo_detection_loss loss · level 0 · unverified · 55394dc469527afa
  3. get_pseudo_labels helper · level 0 · unverified · 493ce76f06838497
  4. trans_angle data_transform · level 1 · ran · our draft was wrong · 5fcf347710b4be86
  5. trans_center data_transform · level 0 · unverified · a3178bc8fc8015c2
  6. trans_size data_transform · level 1 · ran · our draft was wrong · 1411dfea7f7ed8cd
  7. compute_box_and_sem_cls_loss helper · level 0 · unverified · 09393aa9e8d8ad6b
  8. compute_objectness_gt helper · level 0 · unverified · 619751b3a15daea6
  9. compute_objectness_loss helper · level 0 · unverified · cd1cc668b7388a0c
  10. compute_iou_labels helper · level 0 · unverified · 75ff5a97f8ffda97
  11. flip_axis_to_camera helper · level 1 · ran · honoured contract · eddd23cbbb297813
  12. get_3d_box helper · level 1 · ran; the contract check could not run (RAISES) · 2d07150ed0255867
  13. lhs_3d_faster_samecls helper · level 1 · ran; the contract check could not run (RAISES) · 8524fa3afc82724b
  14. huber_loss helper · level 1 · ran · our draft was wrong · bd237d8a9c8b33f6
  15. nn_distance helper · level 1 · ran · our draft was wrong · debfd9f8a49596b7
  16. nn_distance_withcls helper · level 1 · ran · our draft was wrong · 3c3fa3ae7dd47d03
  17. box3d_iou_batch_gpu helper · level 0 · unverified · 4e7246c36ad9782e
  18. roty helper · level 1 · ran · honoured contract · e1f78f900f99690f

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="2401.05011") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

3D Object DetectionData AugmentationObject DetectionPseudo Labelobject-detection

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