Papers › WeakMCN: Multi-task Collaborative Network for Weakly Supervised Referring Expression...

WeakMCN: Multi-task Collaborative Network for Weakly Supervised Referring Expression Comprehension and Segmentation

24 May 2025CVPR 2025 1arXiv:2505.18686archive 2025-07-28

Yang Liu, Silin Cheng, Xinwei He, Sebastien Ourselin, Lei Tan, Gen Luo

Weakly supervised referring expression comprehension(WREC) and segmentation(WRES) aim to learn object grounding based on a given expression using weak supervision signals like image-text pairs. While these tasks have traditionally been modeled separately, we argue that they can benefit from joint learning in a multi-task framework. To this end, we propose WeakMCN, a novel multi-task collaborative network that effectively combines WREC and WRES with a dual-branch architecture. Specifically, the WREC branch is formulated as anchor-based contrastive learning, which also acts as a teacher to supervise the WRES branch. In WeakMCN, we propose two innovative designs to facilitate multi-task collaboration, namely Dynamic Visual Feature Enhancement(DVFE) and Collaborative Consistency Module(CCM). DVFE dynamically combines various pre-trained visual knowledge to meet different task requirements, while CCM promotes cross-task consistency from the perspective of optimization. Extensive experimental results on three popular REC and RES benchmarks, i.e., RefCOCO, RefCOCO+, and RefCOCOg, consistently demonstrate performance gains of WeakMCN over state-of-the-art single-task alternatives, e.g., up to 3.91% and 13.11% on RefCOCO for WREC and WRES tasks, respectively. Furthermore, experiments also validate the strong generalization ability of WeakMCN in both semi-supervised REC and RES settings against existing methods, e.g., +8.94% for semi-REC and +7.71% for semi-RES on 1% RefCOCO. The code is publicly available at https://github.com/MRUIL/WeakMCN.

PaperPDFConference PDFCode 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 24 code samples harvested from 1 repository linked to this paper: 14 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 6 where Syntology's instrument failed) · 10 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: found in paper text by Syntology: 24 samples from 1 repository, 14 ran (8 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 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.

MRUIL/WeakMCN found in paper text by SyntologySyntology: 24 samples, 14 ran (6 instrument-failed) · 10 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

24 samples harvested: 14 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 6 where Syntology's instrument failed) · 10 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.

6ran · our draft was wrong
8ran
10unverified

Licence: 24 of the 24 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 MRUIL/WeakMCN. “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.

MRUIL/WeakMCN found in paper text by Syntology 24 samples, 14 ran (6 instrument-failed) · 10 unverified
CollectDiffuseAttention models/weakmcn/net.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 67bc8a6d67479140 · report fixture: signature q:Tensor/3/float, kc:Tensor/3/float, kd:Tensor/3/float, v:Tensor/3/float, mask:NoneType/0/? · returned tuple · level recorded 2026-09-22
GaranAttention models/weakmcn/net.py ran no licence file found · pointer only · 7bc9eff4f4d99663 · report fixture: signature q:Tensor/2/float, v:Tensor/4/float, mask:NoneType/0/? · returned tuple · level recorded 2026-09-24
LayerNorm in 121 papers
census: 5 implementations from 5 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
models/weakmcn/net.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 9ea9c6ce2b998b41 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
MultiScaleFusion models/weakmcn/net.py ran · metamorphic tier: deterministic no licence file found · pointer only · b60e879191e1ba0b · report fixture: signature x:list/1/Tensor · returned list · level recorded 2026-09-22
PositionEmbeddingSine in 21 papers
census: 6 implementations from 6 papers, 3 distinct outputs across 3 buckets, one shared input per bucket
models/weakmcn/net.py ran · metamorphic tier: invariant no licence file found · pointer only · 02042439d613744f · report fixture: signature positions:Tensor/3/float · returned Tensor · level recorded 2026-09-22
REShead models/weakmcn/net.py ran fingerprinted no licence file found · pointer only · 11a8a18811db0245 · report fixture: signature yin:Tensor/4/float, x_label:NoneType/0/?, y_label:Tensor/4/float, pred_boxes:Tensor/3/float, epoch:int/0/int · returned tuple · level recorded 2026-09-24
SimpleFusion models/weakmcn/net.py ran no licence file found · pointer only · e9842d1e14c284fd · report fixture: signature x:Tensor/4/float, y:Tensor/2/float · returned Tensor · level recorded 2026-09-24
aspp_decoder models/weakmcn/net.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · daa0b79f2cfb71e2 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
clip_boxes_to_image models/weakmcn/net.py ran · our draft was wrong no licence file found · pointer only · 7fd33c7e7a168e3c · report fixture: signature pred_boxes:Tensor/3/float, info_iter:Tensor/2/float · returned Tensor · level recorded 2026-09-22
compute_project_term models/weakmcn/net.py ran · our draft was wrong no licence file found · pointer only · 10e8c98daabb20aa · report fixture: signature mask_scores:Tensor/4/float, gt_bitmasks:Tensor/4/float, seg_weight:Tensor/1/float · returned Tensor · level recorded 2026-09-24
darknet_conv models/weakmcn/net.py ran · our draft was wrong no licence file found · pointer only · 2dee2b39b1176684 · report fixture: signature in_ch:int/0/int, out_ch:int/0/int, ksize:int/0/int, stride:int/0/int, dilation_rate:int/0/int · returned Sequential · level recorded 2026-09-22
dice_coefficient in 17 papers models/weakmcn/net.py ran · our draft was wrong fingerprinted no licence file found · pointer only · dbd6ffe2babb099d · report fixture: signature x:Tensor/2/float, target:Tensor/2/float · returned Tensor · level recorded 2026-09-22
make_mask in 16 papers models/weakmcn/net.py ran · our draft was wrong fingerprinted no licence file found · pointer only · e766a0a3063c15d0 · report fixture: signature feature:Tensor/3/float · returned Tensor · level recorded 2026-09-22
mask_iou_batch models/weakmcn/net.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 155730105dac2066 · report fixture: signature mask1:Tensor/4/float, mask2:Tensor/4/float · returned Tensor · level recorded 2026-09-22
AttFlat models/weakmcn/net.py unverified no licence file found · pointer only · 72dffa3c7226201a · report
LSTM_SA models/weakmcn/net.py unverified no licence file found · pointer only · 4704387a9b5f7285 · report
MHAtt in 6 papers models/weakmcn/net.py unverified no licence file found · pointer only · 31f30cf887eea37f · report
Net in 54 papers models/weakmcn/net.py unverified no licence file found · pointer only · a5498ad0283f9b53 · report
SA in 11 papers models/weakmcn/net.py unverified no licence file found · pointer only · 3e99f267979e0326 · report
WeakREChead models/weakmcn/net.py unverified no licence file found · pointer only · 057f206d4177553f · report
build_efficient_sam_vits models/weakmcn/net.py unverified no licence file found · pointer only · 712223be22da0a31 · report
build_efficient_sam_vitt models/weakmcn/net.py unverified no licence file found · pointer only · 03a654b616fb3ac4 · report
language_encoder models/weakmcn/net.py unverified no licence file found · pointer only · c60d1a9d52f76f07 · report
visual_encoder models/weakmcn/net.py unverified no licence file found · pointer only · 3386a96be793aa64 · 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 WeakMCN (graph method: WeakMCN). 27 bricks; individually on a fixture: 16 ran (of which 2 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 6 where Syntology's instrument failed) · 11 unverified. The assembly has not been run end-to-end.

  1. Net entry · level 0 · unverified · a5498ad0283f9b53
  2. GaranAttention helper · level 1 · ran · 7bc9eff4f4d99663
  3. MultiScaleFusion helper · level 1 · ran · b60e879191e1ba0b
  4. PositionEmbeddingSine helper · level 1 · ran · 02042439d613744f
  5. REShead model · level 1 · ran · 11a8a18811db0245
  6. SimpleFusion helper · level 1 · ran · e9842d1e14c284fd
  7. WeakREChead model · level 0 · unverified · 057f206d4177553f
  8. build_efficient_sam_vits helper · level 0 · unverified · 712223be22da0a31
  9. build_efficient_sam_vitt helper · level 0 · unverified · 03a654b616fb3ac4
  10. clip_boxes_to_image helper · level 1 · ran · our draft was wrong · 7fd33c7e7a168e3c
  11. language_encoder helper · level 0 · unverified · c60d1a9d52f76f07
  12. visual_encoder model · level 0 · unverified · 3386a96be793aa64
  13. CollectDiffuseAttention helper · level 1 · ran · 67bc8a6d67479140
  14. darknet_conv helper · level 1 · ran · our draft was wrong · 2dee2b39b1176684
  15. aspp_decoder helper · level 1 · ran · daa0b79f2cfb71e2
  16. compute_project_term helper · level 1 · ran · our draft was wrong · 10e8c98daabb20aa
  17. mask_iou_batch helper · level 1 · ran · our draft was wrong · 155730105dac2066
  18. dice_coefficient helper · level 1 · ran · our draft was wrong · dbd6ffe2babb099d
  19. AttFlat helper · level 0 · unverified · 72dffa3c7226201a
  20. FC helper · level 1 · ran · 05b99b050c8b7491
  21. FFN helper · level 0 · unverified · cc10a482843ff5dd
  22. LSTM_SA helper · level 0 · unverified · 4704387a9b5f7285
  23. LayerNorm helper · level 1 · ran · 9ea9c6ce2b998b41
  24. MHAtt helper · level 0 · unverified · 31f30cf887eea37f
  25. MLP helper · level 1 · ran · 14b57ad597a09b12
  26. SA helper · level 0 · unverified · 3e99f267979e0326
  27. make_mask helper · level 1 · ran · our draft was wrong · e766a0a3063c15d0

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="2505.18686") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Contrastive LearningReferring ExpressionReferring Expression Comprehension

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