Papers › PolyFormer: Referring Image Segmentation as Sequential Polygon Generation

PolyFormer: Referring Image Segmentation as Sequential Polygon Generation

14 Feb 2023CVPR 2023 1arXiv:2302.07387archive 2025-07-28

Jiang Liu, Hui Ding, Zhaowei Cai, Yuting Zhang, Ravi Kumar Satzoda, Vijay Mahadevan, R. Manmatha

In this work, instead of directly predicting the pixel-level segmentation masks, the problem of referring image segmentation is formulated as sequential polygon generation, and the predicted polygons can be later converted into segmentation masks. This is enabled by a new sequence-to-sequence framework, Polygon Transformer (PolyFormer), which takes a sequence of image patches and text query tokens as input, and outputs a sequence of polygon vertices autoregressively. For more accurate geometric localization, we propose a regression-based decoder, which predicts the precise floating-point coordinates directly, without any coordinate quantization error. In the experiments, PolyFormer outperforms the prior art by a clear margin, e.g., 5.40% and 4.52% absolute improvements on the challenging RefCOCO+ and RefCOCOg datasets. It also shows strong generalization ability when evaluated on the referring video segmentation task without fine-tuning, e.g., achieving competitive 61.5% J&F on the Ref-DAVIS17 dataset.

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 6 code samples harvested from 1 repository linked to this paper: 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 6 samples from 1 repository, 5 ran (4 with no instrument failure; 1 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.

amazon-science/polygon-transformer officialmentioned on GitHubpytorchApache-2.0Syntology: 6 samples, 5 ran (1 instrument-failed) · 1 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

6 samples harvested: 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 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.

1ran · our draft was wrong
4ran
1unverified

Licence: 6 of the 6 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 amazon-science/polygon-transformer. “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.

amazon-science/polygon-transformer official repository 6 samples, 5 ran (1 instrument-failed) · 1 unverified
BatchNorm2d in 9 papers models/polyformer/unify_transformer.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · f18199d037514305 · report fixture: signature out_chan:int/0/int, momentum:float/0/float, eps:float/0/float · returned SyncBatchNorm · level recorded 2026-09-24
drop_path in 325 papers
census: 27 implementations from 61 papers, 5 distinct outputs across 2 buckets, one shared input per bucket
models/polyformer/unify_transformer_layer.py ran fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only · 90fa02b8cae75fe7 · report fixture: signature x:Tensor/3/float, drop_prob:float/0/float, training:bool/0/bool · returned Tensor · level recorded 2026-09-24
make_image_bucket_position models/polyformer/unify_transformer.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · fba339cb809b27fe · report fixture: signature bucket_size:int/0/int, num_relative_distance:int/0/int · returned Tensor · level recorded 2026-09-24
make_token_bucket_position models/polyformer/unify_transformer.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · c0b56d6f87906655 · report fixture: signature bucket_size:int/0/int, max_position:int/0/int · returned Tensor · level recorded 2026-09-24
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 Apache-2.0 recorded; this copy not marked cleared · pointer only · 22b41155e451683b · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
load_tf_weights_in_bert in 135 papers bert/modeling_bert.py unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · fb9398de2966d6de · report

Tasks

DecoderImage SegmentationQuantizationReferring Expression ComprehensionReferring Expression SegmentationSegmentationSemantic SegmentationVideo SegmentationVideo Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Referring Expression Segmentation DAVIS 2017 (val) PolyFormer-B J&F 1st frame 60.9 #8 of 18 Archive leaderboard report
Referring Expression Segmentation DAVIS 2017 (val) PolyFormer-B Zero-Shot Transfer true #8 of 18 Archive leaderboard report
Referring Expression Segmentation RefCOCO+ test B PolyFormer-L Mean IoU 66.73 #12 of 30 Archive leaderboard report
Referring Expression Segmentation RefCOCO+ test B PolyFormer-L Overall IoU 61.87 #12 of 30 Archive leaderboard report
Referring Expression Segmentation RefCOCO+ test B PolyFormer-B Mean IoU 64.64 #14 of 30 Archive leaderboard report
Referring Expression Segmentation RefCOCO+ test B PolyFormer-B Overall IoU 59.33 #14 of 30 Archive leaderboard report
Referring Expression Segmentation RefCOCO+ testA PolyFormer-L Mean IoU 75.71 #12 of 30 Archive leaderboard report
Referring Expression Segmentation RefCOCO+ testA PolyFormer-L Overall IoU 74.56 #12 of 30 Archive leaderboard report
Referring Expression Segmentation RefCOCO+ testA PolyFormer-B Mean IoU 74.51 #15 of 30 Archive leaderboard report
Referring Expression Segmentation RefCOCO+ testA PolyFormer-B Overall IoU 72.89 #15 of 30 Archive leaderboard report
Referring Expression Segmentation RefCOCO+ val PolyFormer-L Mean IoU 72.15 #16 of 33 Archive leaderboard report
Referring Expression Segmentation RefCOCO+ val PolyFormer-L Overall IoU 69.33 #16 of 33 Archive leaderboard report
Referring Expression Segmentation RefCOCO+ val PolyFormer-B Mean IoU 70.65 #17 of 33 Archive leaderboard report
Referring Expression Segmentation RefCOCO+ val PolyFormer-B Overall IoU 67.64 #17 of 33 Archive leaderboard report
Referring Expression Segmentation RefCOCOg-test PolyFormer-L Mean IoU 71.17 #11 of 18 Archive leaderboard report
Referring Expression Segmentation RefCOCOg-test PolyFormer-L Overall IoU 70.19 #11 of 18 Archive leaderboard report
Referring Expression Segmentation RefCOCOg-test PolyFormer-B Mean IoU 69.88 #12 of 18 Archive leaderboard report
Referring Expression Segmentation RefCOCOg-test PolyFormer-B Overall IoU 69.05 #12 of 18 Archive leaderboard report
Referring Expression Segmentation RefCOCOg-val PolyFormer-L Mean IoU 71.15 #12 of 23 Archive leaderboard report
Referring Expression Segmentation RefCOCOg-val PolyFormer-L Overall IoU 69.2 #12 of 23 Archive leaderboard report
Referring Expression Segmentation RefCOCOg-val PolyFormer-B Mean IoU 69.36 #14 of 23 Archive leaderboard report
Referring Expression Segmentation RefCOCOg-val PolyFormer-B Overall IoU 67.76 #14 of 23 Archive leaderboard report
Referring Expression Segmentation RefCoCo val PolyFormer-L Mean IoU 76.94 #17 of 37 Archive leaderboard report
Referring Expression Segmentation RefCoCo val PolyFormer-L Overall IoU 75.96 #17 of 37 Archive leaderboard report
Referring Expression Segmentation RefCoCo val PolyFormer-B Overall IoU 74.82 #19 of 37 Archive leaderboard report
Referring Expression Segmentation ReferIt PolyFormer-L Mean IoU 67.22 #1 of 3 Archive leaderboard report
Referring Expression Segmentation ReferIt PolyFormer-L Overall IoU 72.6 #1 of 3 Archive leaderboard report
Referring Expression Segmentation ReferIt PolyFormer-B Mean IoU 65.98 #2 of 3 Archive leaderboard report
Referring Expression Segmentation ReferIt PolyFormer-B Overall IoU 71.91 #2 of 3 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.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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