Papers › SegVG: Transferring Object Bounding Box to Segmentation for Visual Grounding

SegVG: Transferring Object Bounding Box to Segmentation for Visual Grounding

3 Jul 2024arXiv:2407.03200archive 2025-07-28

Weitai Kang, Gaowen Liu, Mubarak Shah, Yan Yan

Different from Object Detection, Visual Grounding deals with detecting a bounding box for each text-image pair. This one box for each text-image data provides sparse supervision signals. Although previous works achieve impressive results, their passive utilization of annotation, i.e. the sole use of the box annotation as regression ground truth, results in a suboptimal performance. In this paper, we present SegVG, a novel method transfers the box-level annotation as Segmentation signals to provide an additional pixel-level supervision for Visual Grounding. Specifically, we propose the Multi-layer Multi-task Encoder-Decoder as the target grounding stage, where we learn a regression query and multiple segmentation queries to ground the target by regression and segmentation of the box in each decoding layer, respectively. This approach allows us to iteratively exploit the annotation as signals for both box-level regression and pixel-level segmentation. Moreover, as the backbones are typically initialized by pretrained parameters learned from unimodal tasks and the queries for both regression and segmentation are static learnable embeddings, a domain discrepancy remains among these three types of features, which impairs subsequent target grounding. To mitigate this discrepancy, we introduce the Triple Alignment module, where the query, text, and vision tokens are triangularly updated to share the same space by triple attention mechanism. Extensive experiments on five widely used datasets validate our state-of-the-art (SOTA) performance.

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 31 code samples harvested from 1 repository linked to this paper: 20 ran (of which 15 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 5 where Syntology's instrument failed) · 11 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 31 samples from 1 repository, 20 ran (15 with no instrument failure; 5 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.

weitaikang/segvg officialmentioned in papermentioned on GitHubpytorchSyntology: 31 samples, 20 ran (5 instrument-failed) · 11 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

31 samples harvested: 20 ran (of which 15 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 5 where Syntology's instrument failed) · 11 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.

5ran · our draft was wrong
15ran
11unverified

Licence: 31 of the 31 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 weitaikang/segvg. “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”. For 4 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

weitaikang/segvg official repository 31 samples, 20 ran (5 instrument-failed) · 11 unverified
Backbone in 17 papers models/SegVG.py ran · metamorphic tier: deterministic no licence file found · pointer only · 3cea0289236abff1 · report fixture: returned Backbone · level recorded 2026-09-22
BackboneBase in 5 papers models/SegVG.py ran · metamorphic tier: deterministic no licence file found · pointer only · 64ed5e61066db71b · report fixture: returned BackboneBase · level recorded 2026-09-22
DETR in 5 papers models/SegVG.py ran · metamorphic tier: deterministic no licence file found · pointer only · 86783d5616cc10ae · report fixture: returned DETR · level recorded 2026-09-22
FrozenBatchNorm2d models/SegVG.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · edab1f7b54761edc · report fixture: returned FrozenBatchNorm2d · level recorded 2026-09-22
Joiner in 6 papers models/SegVG.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 83277abc6189fc0e · report fixture: returned Joiner · level recorded 2026-09-22
MLP in 375 papers models/SegVG.py ran · metamorphic tier: deterministic no licence file found · pointer only · 1630454d42cd8f1e · report fixture: returned MLP · level recorded 2026-09-22
MultiheadAttention in 44 papers models/SegVG.py ran · metamorphic tier: deterministic no licence file found · pointer only · d232f407f48ea631 · report fixture: returned MultiheadAttention · level recorded 2026-09-22
NestedTensor in 24 papers models/SegVG.py ran · metamorphic tier: deterministic no licence file found · pointer only · b636bcda4557023e · report fixture: returned NestedTensor · level recorded 2026-09-22
PositionEmbeddingLearned in 12 papers models/SegVG.py ran · metamorphic tier: deterministic no licence file found · pointer only · b088aa9b061f576f · report fixture: returned PositionEmbeddingLearned · 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/SegVG.py ran no licence file found · pointer only · f6738d0ca7aecfc9 · report fixture: returned PositionEmbeddingSine · level recorded 2026-09-22
TransformerDecoder in 49 papers models/SegVG.py ran · metamorphic tier: deterministic no licence file found · pointer only · 3f84d490190e415e · report fixture: returned TransformerDecoder · level recorded 2026-09-22
TransformerDecoderLayer in 45 papers models/SegVG.py ran · metamorphic tier: deterministic no licence file found · pointer only · cb39d54bf9488205 · report fixture: returned TransformerDecoderLayer · level recorded 2026-09-22
TransformerEncoder in 96 papers models/SegVG.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 143c12efbf5e86a7 · report fixture: returned TransformerEncoder · level recorded 2026-09-22
TransformerEncoderLayer in 90 papers models/SegVG.py ran no licence file found · pointer only · 11325595a1e21029 · report fixture: returned TransformerEncoderLayer · level recorded 2026-09-22
Triple_Alignment models/SegVG.py ran · metamorphic tier: deterministic no licence file found · pointer only · 8fadf62d0de39848 · report fixture: returned Triple_Alignment · level recorded 2026-09-22
_get_activation_fn in 21 papers models/SegVG.py ran · our draft was wrong no licence file found · pointer only · 0bb264f52e707e08 · report fixture: signature activation:str/0/str · returned function · level recorded 2026-09-22
_get_clones in 28 papers models/SegVG.py ran · our draft was wrong no licence file found · pointer only · a8f1bbeb369e1829 · report fixture: signature module:callable/0/?, N:int/0/int · returned ModuleList · level recorded 2026-09-22
build_backbone in 29 papers models/SegVG.py ran · our draft was wrong no licence file found · pointer only · f07174e325e1d5a1 · report fixture: signature args:SimpleArgs/0/? · returned Joiner · level recorded 2026-09-22
build_position_encoding in 42 papers models/SegVG.py ran · our draft was wrong no licence file found · pointer only · 153726d9d215fcbd · report fixture: signature args:Args/0/? · returned PositionEmbeddingSine · level recorded 2026-09-22
nested_tensor_from_tensor_list in 60 papers models/SegVG.py ran · our draft was wrong no licence file found · pointer only · a7b239b27e836fef · report fixture: signature tensor_list:list/1/Tensor · returned NestedTensor · level recorded 2026-09-22
CustomBertModelLayers models/SegVG.py unverified no licence file found · pointer only · 98a92778fc361b78 · report
SegVG models/SegVG.py unverified no licence file found · pointer only · a46b55dedcf54d6a · report
Transformer in 173 papers models/SegVG.py unverified no licence file found · pointer only · 7e21dc328864a039 · report
Triple_Alignment_MHA models/SegVG.py unverified no licence file found · pointer only · b2c1a11b8bad9f0f · report
VisionLanguageDecoder models/SegVG.py unverified no licence file found · pointer only · be0f0a78676af033 · report
VisionLanguageEncoder models/SegVG.py unverified no licence file found · pointer only · a9723207bca49592 · report
_onnx_nested_tensor_from_tensor_list in 9 papers models/SegVG.py unverified no licence file found · pointer only · 18ab6b8c9071badc · report
build_bert models/SegVG.py unverified no licence file found · pointer only · d094d16051634f8d · report
build_detr models/SegVG.py unverified no licence file found · pointer only · 6dde8f71aadd6481 · report
build_transformer in 62 papers models/SegVG.py unverified no licence file found · pointer only · 9008729eeca3ae5e · report
build_vl_transformer in 6 papers models/SegVG.py unverified no licence file found · pointer only · fa56b4b60f836e92 · 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 SegVG (graph method: SegVG). 32 bricks; individually on a fixture: 21 ran (of which 15 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 0 violated, 15 with no contract checked; 5 where Syntology's instrument failed) · 11 unverified. The assembly has not been run end-to-end.

  1. SegVG entry · level 0 · unverified · a46b55dedcf54d6a
  2. MLP helper · level 1 · ran · 1630454d42cd8f1e
  3. Triple_Alignment model · level 1 · ran · 8fadf62d0de39848
  4. VisionLanguageDecoder helper · level 0 · unverified · be0f0a78676af033
  5. build_bert helper · level 0 · unverified · d094d16051634f8d
  6. build_detr helper · level 0 · unverified · 6dde8f71aadd6481
  7. build_vl_transformer helper · level 0 · unverified · fa56b4b60f836e92
  8. Triple_Alignment_MHA helper · level 0 · unverified · b2c1a11b8bad9f0f
  9. _get_clones helper · level 1 · ran · our draft was wrong · a8f1bbeb369e1829
  10. TransformerDecoder helper · level 1 · ran · 3f84d490190e415e
  11. TransformerDecoderLayer helper · level 1 · ran · cb39d54bf9488205
  12. CustomBertModelLayers helper · level 0 · unverified · 98a92778fc361b78
  13. DETR helper · level 1 · ran · 86783d5616cc10ae
  14. build_backbone helper · level 1 · ran · our draft was wrong · f07174e325e1d5a1
  15. build_transformer helper · level 0 · unverified · 9008729eeca3ae5e
  16. VisionLanguageEncoder model · level 0 · unverified · a9723207bca49592
  17. MultiheadAttention model · level 1 · ran · d232f407f48ea631
  18. _get_activation_fn helper · level 1 · ran · our draft was wrong · 0bb264f52e707e08
  19. NestedTensor helper · level 1 · ran · b636bcda4557023e
  20. nested_tensor_from_tensor_list helper · level 1 · ran · our draft was wrong · a7b239b27e836fef
  21. Backbone helper · level 1 · ran · 3cea0289236abff1
  22. Joiner helper · level 1 · ran · 83277abc6189fc0e
  23. build_position_encoding helper · level 1 · ran · our draft was wrong · 153726d9d215fcbd
  24. Transformer helper · level 0 · unverified · 7e21dc328864a039
  25. TransformerEncoder helper · level 1 · ran · 143c12efbf5e86a7
  26. TransformerEncoderLayer model · level 1 · ran · 11325595a1e21029
  27. _max_by_axis helper · level 1 · ran · honoured contract · ef393284ce3c9ea1
  28. _onnx_nested_tensor_from_tensor_list helper · level 0 · unverified · 18ab6b8c9071badc
  29. BackboneBase helper · level 1 · ran · 64ed5e61066db71b
  30. FrozenBatchNorm2d helper · level 1 · ran · edab1f7b54761edc
  31. PositionEmbeddingLearned helper · level 1 · ran · b088aa9b061f576f
  32. PositionEmbeddingSine helper · level 1 · ran · f6738d0ca7aecfc9

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="2407.03200") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Object DetectionSegmentationVisual Groundingobject-detectionregression

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AttentionSoftmax

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