Papers › Mask Grounding for Referring Image Segmentation

Mask Grounding for Referring Image Segmentation

19 Dec 2023CVPR 2024 1arXiv:2312.12198archive 2025-07-28

Yong Xien Chng, Henry Zheng, Yizeng Han, Xuchong Qiu, Gao Huang

Referring Image Segmentation (RIS) is a challenging task that requires an algorithm to segment objects referred by free-form language expressions. Despite significant progress in recent years, most state-of-the-art (SOTA) methods still suffer from considerable language-image modality gap at the pixel and word level. These methods generally 1) rely on sentence-level language features for language-image alignment and 2) lack explicit training supervision for fine-grained visual grounding. Consequently, they exhibit weak object-level correspondence between visual and language features. Without well-grounded features, prior methods struggle to understand complex expressions that require strong reasoning over relationships among multiple objects, especially when dealing with rarely used or ambiguous clauses. To tackle this challenge, we introduce a novel Mask Grounding auxiliary task that significantly improves visual grounding within language features, by explicitly teaching the model to learn fine-grained correspondence between masked textual tokens and their matching visual objects. Mask Grounding can be directly used on prior RIS methods and consistently bring improvements. Furthermore, to holistically address the modality gap, we also design a cross-modal alignment loss and an accompanying alignment module. These additions work synergistically with Mask Grounding. With all these techniques, our comprehensive approach culminates in MagNet (Mask-grounded Network), an architecture that significantly outperforms prior arts on three key benchmarks (RefCOCO, RefCOCO+ and G-Ref), demonstrating our method's effectiveness in addressing current limitations of RIS algorithms. Our code and pre-trained weights will be released.

PaperPDFConference PDFCodeCode Syntology ran

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 13 code samples harvested from 1 repository linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 8 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 7 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 13 samples from 1 repository, 10 ran (2 with no instrument failure; 8 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. 5 of the 10 samples that ran have no recorded date.

yxchng/mask-grounding officialmentioned on GitHubpytorchAGPL-3.0Syntology: 13 samples, 10 ran (8 instrument-failed) · 3 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

13 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 8 where Syntology's instrument failed) · 3 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.

7ran · our draft was wrong
1ran; the contract check could not run
2ran
3unverified

Licence: 13 of the 13 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 yxchng/mask-grounding. “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.

yxchng/mask-grounding official repository 13 samples, 10 ran (8 instrument-failed) · 3 unverified
swish in 258 papers
census: 14 implementations from 37 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
bert/activations.py ran · our draft was wrong fingerprinted AGPL-3.0 (copyleft) · pointer only · 0f786c407fb1ee4c · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded
window_partition in 377 papers
census: 13 implementations from 17 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
lib/backbone.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted AGPL-3.0 (copyleft) · pointer only · 144d10b49baeb8a6 · report fixture: signature x:Tensor/4/float, window_size:int/0/int · returned Tensor · level recorded, date not recorded
find_pruneable_heads_and_indices in 19 papers bert/modeling_utils.py ran AGPL-3.0 (copyleft) · pointer only · b239247b87d4f3dc · report fixture: signature heads:list/1/int, n_heads:int/0/int, head_size:int/0/int, already_pruned_heads:set/0/? · returned tuple · level recorded 2026-09-24
gelu_fast in 39 papers bert/activations.py ran · our draft was wrong fingerprinted AGPL-3.0 (copyleft) · pointer only · a4475703ff58ecf9 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded
gelu_new in 55 papers
census: 3 implementations from 7 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
bert/activations.py ran · our draft was wrong fingerprinted AGPL-3.0 (copyleft) · pointer only · dc9ffc0f29e7fa3d · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded
mish in 95 papers
census: 5 implementations from 8 papers, 1 distinct output on one shared input
bert/modeling_bert.py ran · our draft was wrong fingerprinted AGPL-3.0 (copyleft) · pointer only · 22b41155e451683b · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
pad_if_smaller in 5 papers transforms.py ran AGPL-3.0 (copyleft) · pointer only · 452475fb6da97402 · report fixture: signature img:Image/0/?, size:int/0/int, fill:int/0/int · returned Image · level recorded 2026-09-24
prune_conv1d_layer in 20 papers bert/modeling_utils.py ran · our draft was wrong AGPL-3.0 (copyleft) · pointer only · b3ee64494a3b6d38 · report fixture: signature layer:callable/0/?, index:Tensor/1/int, dim:int/0/int · returned Conv1D · level recorded 2026-09-24
prune_linear_layer in 40 papers bert/modeling_utils.py ran · our draft was wrong AGPL-3.0 (copyleft) · pointer only · a37615738b3ddcd3 · report fixture: signature layer:callable/0/?, index:Tensor/1/int, dim:int/0/int · returned Linear · level recorded 2026-09-24
window_reverse in 296 papers lib/backbone.py ran · our draft was wrong AGPL-3.0 (copyleft) · pointer only · 61bf152e6a42a184 · report fixture: signature windows:Tensor/4/float, window_size:int/0/int, H:int/0/int, W:int/0/int · returned Tensor · level recorded, date not recorded
lavt lib/multimodal_segmentation.py unverified AGPL-3.0 (copyleft) · pointer only · 67fee1d4b5d4493d · report
lavt_one lib/multimodal_segmentation.py unverified AGPL-3.0 (copyleft) · pointer only · 2944cc78660b63ff · report
load_tf_weights_in_bert in 135 papers bert/modeling_bert.py unverified AGPL-3.0 (copyleft) · pointer only · fb9398de2966d6de · report

Tasks

Image SegmentationReferring Expression SegmentationSegmentationSemantic SegmentationSentenceVisual Groundingcross-modal alignment

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Referring Expression Segmentation RefCOCO testA MagNet Overall IoU 78.24 #10 of 13 Archive leaderboard report
Referring Expression Segmentation RefCOCO testB MagNet Overall IoU 71.05 #10 of 13 Archive leaderboard report
Referring Expression Segmentation RefCOCO+ test B MagNet Overall IoU 58.14 #15 of 30 Archive leaderboard report
Referring Expression Segmentation RefCOCO+ testA MagNet Overall IoU 71.32 #16 of 30 Archive leaderboard report
Referring Expression Segmentation RefCOCO+ val MagNet Overall IoU 66.16 #19 of 33 Archive leaderboard report
Referring Expression Segmentation RefCOCOg-test MagNet Overall IoU 66.03 #14 of 18 Archive leaderboard report
Referring Expression Segmentation RefCOCOg-val MagNet Overall IoU 65.36 #16 of 23 Archive leaderboard report
Referring Expression Segmentation RefCoCo val MagNet Overall IoU 75.24 #18 of 37 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