Papers › All Points Matter: Entropy-Regularized Distribution Alignment for Weakly-supervised 3D...

All Points Matter: Entropy-Regularized Distribution Alignment for Weakly-supervised 3D Segmentation

25 May 2023NeurIPS 2023 11arXiv:2305.15832archive 2025-07-28

Liyao Tang, Zhe Chen, Shanshan Zhao, Chaoyue Wang, DaCheng Tao

Pseudo-labels are widely employed in weakly supervised 3D segmentation tasks where only sparse ground-truth labels are available for learning. Existing methods often rely on empirical label selection strategies, such as confidence thresholding, to generate beneficial pseudo-labels for model training. This approach may, however, hinder the comprehensive exploitation of unlabeled data points. We hypothesize that this selective usage arises from the noise in pseudo-labels generated on unlabeled data. The noise in pseudo-labels may result in significant discrepancies between pseudo-labels and model predictions, thus confusing and affecting the model training greatly. To address this issue, we propose a novel learning strategy to regularize the generated pseudo-labels and effectively narrow the gaps between pseudo-labels and model predictions. More specifically, our method introduces an Entropy Regularization loss and a Distribution Alignment loss for weakly supervised learning in 3D segmentation tasks, resulting in an ERDA learning strategy. Interestingly, by using KL distance to formulate the distribution alignment loss, it reduces to a deceptively simple cross-entropy-based loss which optimizes both the pseudo-label generation network and the 3D segmentation network simultaneously. Despite the simplicity, our method promisingly improves the performance. We validate the effectiveness through extensive experiments on various baselines and large-scale datasets. Results show that ERDA effectively enables the effective usage of all unlabeled data points for learning and achieves state-of-the-art performance under different settings. Remarkably, our method can outperform fully-supervised baselines using only 1% of true annotations. Code and model will be made publicly available at https://github.com/LiyaoTang/ERDA.

PaperPDFConference PDFCodeCode 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 33 code samples harvested from 1 repository linked to this paper: 16 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 13 where Syntology's instrument failed) · 17 unverified. Where Syntology's instrument failed: 11 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: 33 samples from 1 repository, 16 ran (3 with no instrument failure; 13 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 between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

LiyaoTang/ERDA officialmentioned in papertfSyntology: 33 samples, 16 ran (13 instrument-failed) · 17 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

33 samples harvested: 16 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 13 where Syntology's instrument failed) · 17 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
1ran · violated contract
11ran · our draft was wrong
2ran; the contract check could not run
17unverified

Licence: 0 of the 33 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 LiyaoTang/ERDA. “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.

LiyaoTang/ERDA official repository 33 samples, 16 ran (13 instrument-failed) · 17 unverified
apply_reduction models/head.py ran; the contract check could not run (RAISES) MIT (permissive) · 65566e34fbee2d02 · report fixture: signature target:EagerTensor/3/float, reduction:str/0/str, mask:EagerTensor/2/float, axis:int/0/int · returned EagerTensor · level recorded 2026-09-24
check_mask models/head.py ran · violated contract fingerprinted MIT (permissive) · 585514b22f60ec47 · report fixture: signature x:EagerTensor/3/float, mask:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-22
dropout in 34 papers models/head.py ran · our draft was wrong fingerprinted MIT (permissive) · 66f4ca8e47d66009 · report fixture: signature features:EagerTensor/2/float, rate:float/0/float, is_training:EagerTensor/0/bool, noise_shape:NoneType/0/? · returned EagerTensor · level recorded 2026-09-22
fetch_supports_stage models/head.py ran · our draft was wrong MIT (permissive) · 9166f0042b70f6a0 · report fixture: signature inputs:dict/0/?, stage_n:str/0/str, stage_i:int/0/int, ftype:str/0/str · returned tuple · level recorded 2026-09-24
get_activation in 218 papers models/head.py ran · our draft was wrong MIT (permissive) · 6f022cb10fccee9d · report fixture: signature activation:str/0/str · returned function · level recorded 2026-09-22
get_class_weight models/head.py ran · honoured contract MIT (permissive) · 36d027452f58eb43 · report fixture: signature dataset:str/0/str, labels:NoneType/0/?, weight_type:str/0/str, normalize:str/0/str, version:str/0/str · returned EagerTensor · level recorded 2026-09-24
get_ftype models/head.py ran · our draft was wrong MIT (permissive) · 11f40ad83f37e95f · report fixture: signature ftype:str/0/str, raise_not_found:bool/0/bool · returned tuple · level recorded 2026-09-24
get_initializer in 32 papers models/head.py ran · our draft was wrong MIT (permissive) · b9980bfcdc9fa508 · report fixture: signature k:NoneType/0/? · returned GlorotUniform · level recorded 2026-09-22
get_kwargs in 5 papers models/head.py ran · our draft was wrong MIT (permissive) · 6eb3a7a026e881ba · report fixture: signature block_cfg:BlockConfig/0/?, config:Config/0/?, is_training:bool/0/bool, act:bool/0/bool · returned dict · level recorded 2026-09-24
get_kwargs_mlp models/head.py ran · our draft was wrong MIT (permissive) · a36a27d7a5eeaf3e · report fixture: signature block_cfg:BlockConfig/0/?, config:Config/0/?, is_training:bool/0/bool, act:bool/0/bool, _kwargs:dict/0/? · returned dict · level recorded 2026-09-24
get_type in 7 papers models/head.py ran · our draft was wrong fingerprinted MIT (permissive) · 65a09d51e78e2ff8 · report fixture: signature k:str/0/str · returned DType · level recorded 2026-09-22
masked_softmax in 51 papers
census: 10 implementations from 10 papers, 10 distinct outputs across 6 buckets, one shared input per bucket
models/head.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 72be9593f760bb29 · report fixture: signature vec:EagerTensor/2/float, valid_mask:EagerTensor/2/bool, axis:int/0/int · returned EagerTensor · level recorded 2026-09-22
tf_cond models/head.py ran · honoured contract MIT (permissive) · 0822e0ff9c4729a5 · report fixture: signature pred:EagerTensor/0/bool, true_fn:callable/0/?, false_fn:callable/0/?, name:str/0/str · returned EagerTensor · level recorded 2026-09-22
tf_gather models/head.py ran · our draft was wrong MIT (permissive) · 862351355d71ffc6 · report fixture: signature supports:EagerTensor/3/float, neighbor_idx:EagerTensor/2/int, shadow_fn:callable/0/?, get_mask:bool/0/bool · returned tuple · level recorded 2026-09-24
tf_scope models/head.py ran · our draft was wrong MIT (permissive) · 7153a8b6464f04ea · report fixture: signature func:callable/0/? · returned function · level recorded 2026-09-22
to_valid_stage models/head.py ran · our draft was wrong MIT (permissive) · 532f90a2c87f9f32 · report fixture: signature stage_n:str/0/str, short:bool/0/bool · returned str · level recorded 2026-09-22
_variable_on_cpu models/head.py unverified MIT (permissive) · ce6452caa8be618b · report
_variable_with_weight_decay models/head.py unverified MIT (permissive) · d98ee661d06ca55e · report
batch_norm in 46 papers models/head.py unverified MIT (permissive) · 0c8f88cadeb2d45f · report
calc_dist models/head.py unverified MIT (permissive) · 34736bc6edd358fa · report
calc_loss in 35 papers models/head.py unverified MIT (permissive) · 87082c78c01cdcc8 · report
cls_contrast_head models/head.py unverified MIT (permissive) · 2b0265835b2b9e32 · report
conv1d_1x1 models/head.py unverified MIT (permissive) · 2101a28ba054c714 · report
dense_layer in 9 papers models/head.py unverified MIT (permissive) · 6a695291eaa9bee6 · report
get_sample_idx models/head.py unverified MIT (permissive) · a3a2fe6e67287299 · report
get_scene_label models/head.py unverified MIT (permissive) · 77f37437581eb0b7 · report
mlp_head models/head.py unverified MIT (permissive) · 747ee8f1f284c303 · report
mlps models/head.py unverified MIT (permissive) · 95ee8413bb72a5d2 · report
mlps_by_ops models/head.py unverified MIT (permissive) · b5717e76cb07f225 · report
parse_stage models/head.py unverified MIT (permissive) · c1132af83963c82c · report
pseudo_head models/head.py unverified MIT (permissive) · b62f118649752c42 · report
tf_get_variable models/head.py unverified MIT (permissive) · 5271d891a74ff73e · 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 ERDA (graph method: ERDA). 33 bricks; individually on a fixture: 16 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 13 where Syntology's instrument failed) · 17 unverified. The assembly has not been run end-to-end.

  1. pseudo_head entry · level 0 · unverified · b62f118649752c42
  2. apply_reduction helper · level 1 · ran; the contract check could not run (RAISES) · 65566e34fbee2d02
  3. calc_dist helper · level 0 · unverified · 34736bc6edd358fa
  4. calc_loss helper · level 0 · unverified · 87082c78c01cdcc8
  5. cls_contrast_head helper · level 0 · unverified · 2b0265835b2b9e32
  6. get_ftype helper · level 1 · ran · our draft was wrong · 11f40ad83f37e95f
  7. get_kwargs_mlp helper · level 1 · ran · our draft was wrong · a36a27d7a5eeaf3e
  8. get_sample_idx helper · level 0 · unverified · a3a2fe6e67287299
  9. mlp_head helper · level 0 · unverified · 747ee8f1f284c303
  10. mlps_by_ops helper · level 0 · unverified · b5717e76cb07f225
  11. normalize helper · level 0 · unverified · 114618f6f9dc6b02
  12. tf_cond helper · level 1 · ran · honoured contract · 0822e0ff9c4729a5
  13. tf_gather helper · level 1 · ran · our draft was wrong · 862351355d71ffc6
  14. tf_scope helper · level 1 · ran · our draft was wrong · 7153a8b6464f04ea
  15. check_mask helper · level 1 · ran · violated contract · 585514b22f60ec47
  16. get_initializer helper · level 1 · ran · our draft was wrong · b9980bfcdc9fa508
  17. get_kwargs helper · level 1 · ran · our draft was wrong · 6eb3a7a026e881ba
  18. parse_stage helper · level 0 · unverified · c1132af83963c82c
  19. dense_layer helper · level 0 · unverified · 6a695291eaa9bee6
  20. dropout helper · level 1 · ran · our draft was wrong · 66f4ca8e47d66009
  21. get_class_weight helper · level 1 · ran · honoured contract · 36d027452f58eb43
  22. get_scene_label helper · level 0 · unverified · 77f37437581eb0b7
  23. tf_get_variable helper · level 0 · unverified · 5271d891a74ff73e
  24. mlps helper · level 0 · unverified · 95ee8413bb72a5d2
  25. masked_softmax helper · level 1 · ran; the contract check could not run (RAISES) · 72be9593f760bb29
  26. get_type helper · level 1 · ran · our draft was wrong · 65a09d51e78e2ff8
  27. to_valid_stage helper · level 1 · ran · our draft was wrong · 532f90a2c87f9f32
  28. conv1d_1x1 helper · level 0 · unverified · 2101a28ba054c714
  29. get_activation helper · level 1 · ran · our draft was wrong · 6f022cb10fccee9d
  30. _variable_on_cpu helper · level 0 · unverified · ce6452caa8be618b
  31. _variable_with_weight_decay helper · level 0 · unverified · d98ee661d06ca55e
  32. batch_norm helper · level 0 · unverified · 0c8f88cadeb2d45f
  33. fetch_supports_stage helper · level 1 · ran · our draft was wrong · 9166f0042b70f6a0

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="2305.15832") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

AllPseudo LabelSegmentationWeakly-supervised Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Entropy Regularization

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