Papers › Pix2seq: A Language Modeling Framework for Object Detection

Pix2seq: A Language Modeling Framework for Object Detection

22 Sep 2021ICLR 2022 4arXiv:2109.10852archive 2025-07-28

Ting Chen, Saurabh Saxena, Lala Li, David J. Fleet, Geoffrey Hinton

We present Pix2Seq, a simple and generic framework for object detection. Unlike existing approaches that explicitly integrate prior knowledge about the task, we cast object detection as a language modeling task conditioned on the observed pixel inputs. Object descriptions (e.g., bounding boxes and class labels) are expressed as sequences of discrete tokens, and we train a neural network to perceive the image and generate the desired sequence. Our approach is based mainly on the intuition that if a neural network knows about where and what the objects are, we just need to teach it how to read them out. Beyond the use of task-specific data augmentations, our approach makes minimal assumptions about the task, yet it achieves competitive results on the challenging COCO dataset, compared to highly specialized and well optimized detection algorithms.

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.

Syntology holds a reference implementation of Pix2Seq, generated from the paper text (not the authors' code), at level 3 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='Pix2Seq') (how to connect); the free check have('2109.10852') needs no token.

For agents, on Syntology's MCP service (how to connect):

Code

No sample from the archive's official repository (google-research/pix2seq) is linked to this paper; the 12 samples below come from 5 community repositories. Syntology harvested code from google-research/pix2seq for 2 other papers.

google-research/pix2seq: Syntology's graph links these samples to Scalable Adaptive Computation for Iterative Generation (arXiv:2212.11972; that paper's own run record: 21 ran (of which 9 constructed an object rather than computing a result; 18 with no instrument failure: 8 honoured, 0 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified) and FIT: Far-reaching Interleaved Transformers (arXiv:2305.12689; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method.

Syntology 12 code samples harvested from 5 repositories linked to this paper: 10 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 2 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 12 samples from 5 repositories, 10 ran (6 with no instrument failure; 4 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

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. 1 of the 10 samples that ran has no recorded date.

google-research/pix2seq officialmentioned in papermentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Scalable Adaptive Computation for Iterative Generation (arXiv:2212.11972; that paper's own run record: 21 ran (of which 9 constructed an object rather than computing a result; 18 with no instrument failure: 8 honoured, 0 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified) and FIT: Far-reaching Interleaved Transformers (arXiv:2305.12689; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
moein-shariatnia/Pix2Seq mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
volgachen/Pix2Seq_Pytorch mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified report
gaopengcuhk/Pretrained-Pix2Seq pytorchSyntology: 2 samples, 1 ran (1 instrument-failed) · 1 unverified report
gaopengcuhk/Stable-Pix2Seq pytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
gaopengcuhk/Unofficial-Pix2Seq pytorchApache-2.0Syntology: 6 samples, 5 ran (2 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

12 samples harvested: 10 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 2 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 2 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.

1ran · honoured contract
2ran · violated contract
4ran · our draft was wrong
3ran
2unverified

Licence: 10 of the 12 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 5 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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 1 sample 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.

moein-shariatnia/Pix2Seq community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
EncoderDecoder model.py ran fingerprinted MIT (permissive) · 7261e3dde0bad885 · report fixture: returned EncoderDecoder · level recorded 2026-09-22
volgachen/Pix2Seq_Pytorch community (archive-listed) 2 samples, 2 ran (1 instrument-failed) · 0 unverified
Pix2Seq playground/pix2seq/pix2seq.py ran no licence file found · pointer only · 600431a357e72cd6 · report fixture: returned Pix2Seq · level recorded 2026-09-22
nested_tensor_from_tensor_list in 60 papers playground/pix2seq/pix2seq.py ran · our draft was wrong no licence file found · pointer only · 8542cf00e1274bb3 · report fixture: signature tensor_list:list/1/Tensor, target_list:list/1/dict, fix_input:NoneType/0/? · returned NestedTensor · level recorded 2026-09-22
gaopengcuhk/Pretrained-Pix2Seq community (archive-listed) 2 samples, 1 ran (1 instrument-failed) · 1 unverified
nested_tensor_from_tensor_list in 60 papers playground/pix2seq/pix2seq.py ran · our draft was wrong no licence file found · pointer only · 9b0e434afd6ba1bb · report fixture: signature tensor_list:list/1/Tensor, target_list:list/1/dict · returned NestedTensor · level recorded 2026-09-24
Pix2Seq playground/pix2seq/pix2seq.py unverified no licence file found · pointer only · 6bddc92dacf1a610 · report
gaopengcuhk/Stable-Pix2Seq community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
DETR in 5 papers models/detr.py ran Apache-2.0 (permissive) · 2630ab8a095c33dd · report fixture: returned DETR · level recorded 2026-09-22
gaopengcuhk/Unofficial-Pix2Seq community (archive-listed) 6 samples, 5 ran (2 instrument-failed) · 1 unverified
convert_to_xywh in 26 papers datasets/coco_eval.py ran · honoured contract fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only · f31a58bf6457ced5 · report fixture: signature boxes:Tensor/2/float · returned Tensor · level recorded 2026-09-22
dice_loss in 193 papers
census: 10 implementations from 16 papers, 7 distinct outputs across 4 buckets, one shared input per bucket this sample: bucket 1 of 4, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32
models/segmentation.py ran · violated contract fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only · ac8fe530cdad4d8c · report fixture: signature inputs:Tensor/2/float, targets:Tensor/2/float, num_boxes:int/0/int · returned Tensor · level recorded 2026-09-22
evaluate in 514 papers datasets/coco_eval.py ran · our draft was wrong Apache-2.0 recorded; this copy not marked cleared · pointer only · fe0ddcc2d420c9a0 · report fixture: signature self:MockCOCOEval/0/? · returned tuple · level recorded 2026-09-22
generate_square_subsequent_mask in 30 papers models/transformer.py ran · violated contract fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only · 894b253f35765276 · report fixture: signature sz:int/0/int · returned Tensor · level recorded 2026-09-22
sigmoid_focal_loss in 122 papers
census: 3 implementations from 9 papers, 2 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32
models/segmentation.py ran · our draft was wrong fingerprinted Apache-2.0 recorded; this copy not marked cleared · pointer only · 5c0711aada67957e · report fixture: signature inputs:Tensor/2/float, targets:Tensor/2/float, num_boxes:int/0/int, alpha:float/0/float, gamma:float/0/float · returned Tensor · level recorded, date not recorded
build_transformer in 62 papers models/transformer.py unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · cd17dcaf812b820d · 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. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. 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. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another. Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

5 assemblies on this paper: 4 harvested, 1 generated, listed in 2 groups (siblings lifted in one batch form one group).

generated Assembly for Pix2Seq (graph method: Pix2Seq), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 3; 5 property tests passed on both).

label matches by construction: the code was generated for this method (not judged by a model)

  1. dequantize entry · level 3 · ran · honoured contract · a82340bd4bb1ad94d09ba1621b36767a50aa1e315451b05204d9d3a04701da64

4 sibling assemblies for Pix2Seq (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Pix2Seq (graph method: Pix2Seq). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 4 siblings

  1. EncoderDecoder entry · level 1 · ran · 7261e3dde0bad885

harvested Assembly for Pix2Seq (graph method: Pix2Seq). 6 bricks; individually on a fixture: 5 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 4 siblings

  1. DETR entry · level 1 · ran · 2630ab8a095c33dd
  2. MLP helper · level 1 · ran · d71ab24dd4408288
  3. NestedTensor helper · level 1 · ran · b636bcda4557023e
  4. nested_tensor_from_tensor_list helper · level 1 · ran · our draft was wrong · 9277ea2a21aca6f8
  5. _max_by_axis helper · level 1 · ran · honoured contract · ef393284ce3c9ea1
  6. _onnx_nested_tensor_from_tensor_list helper · level 0 · unverified · 0ff86335d5b895ad

harvested Assembly for Pix2Seq (graph method: Pix2Seq). 5 bricks; individually on a fixture: 4 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 4 siblings

  1. Pix2Seq entry · level 1 · ran · 600431a357e72cd6
  2. nested_tensor_from_tensor_list helper · level 1 · ran · our draft was wrong · 8542cf00e1274bb3
  3. NestedTensor helper · level 1 · ran · b636bcda4557023e
  4. _max_by_axis helper · level 1 · ran · honoured contract · ef393284ce3c9ea1
  5. _onnx_nested_tensor_from_tensor_list helper · level 0 · unverified · 0ff86335d5b895ad

harvested Assembly for Pix2Seq (graph method: Pix2Seq). 6 bricks; individually on a fixture: 4 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 4 siblings

  1. Pix2Seq entry · level 0 · unverified · 6bddc92dacf1a610
  2. box_cxcywh_to_xyxy helper · level 1 · ran · honoured contract · e0a06ded5d4f6c3c
  3. nested_tensor_from_tensor_list helper · level 1 · ran · our draft was wrong · 9b0e434afd6ba1bb
  4. NestedTensor helper · level 1 · ran · b636bcda4557023e
  5. _max_by_axis helper · level 1 · ran · honoured contract · ef393284ce3c9ea1
  6. _onnx_nested_tensor_from_tensor_list helper · level 0 · unverified · 0ff86335d5b895ad

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="2109.10852") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Language ModelingLanguage ModellingObjectObject Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection COCO minival Pix2seq (ViT-L) box AP 50.0 #81 of 220 Archive leaderboard report
Object Detection COCO minival Pix2seq (R50-C4) box AP 47.3 #97 of 220 Archive leaderboard report
Object Detection COCO minival Pix2seq (ViT-B) box AP 47.1 #98 of 220 Archive leaderboard report
Object Detection COCO minival Pix2seq (R101-DC5) AP50 63.2 #118 of 220 Archive leaderboard report
Object Detection COCO minival Pix2seq (R101-DC5) AP75 48.6 #118 of 220 Archive leaderboard report
Object Detection COCO minival Pix2seq (R101-DC5) APL 60.4 #118 of 220 Archive leaderboard report
Object Detection COCO minival Pix2seq (R101-DC5) APM 48.9 #118 of 220 Archive leaderboard report
Object Detection COCO minival Pix2seq (R101-DC5) APS 28.2 #118 of 220 Archive leaderboard report
Object Detection COCO minival Pix2seq (R101-DC5) box AP 45.0 #118 of 220 Archive leaderboard report
Object Detection COCO minival Pix2seq (R50-DC5 ) AP50 61.0 #142 of 220 Archive leaderboard report
Object Detection COCO minival Pix2seq (R50-DC5 ) AP75 46.1 #142 of 220 Archive leaderboard report
Object Detection COCO minival Pix2seq (R50-DC5 ) APL 58.6 #142 of 220 Archive leaderboard report
Object Detection COCO minival Pix2seq (R50-DC5 ) APM 47 #142 of 220 Archive leaderboard report
Object Detection COCO minival Pix2seq (R50-DC5 ) APS 26.6 #142 of 220 Archive leaderboard report
Object Detection COCO minival Pix2seq (R50-DC5 ) box AP 43.2 #142 of 220 Archive leaderboard report
Object Detection COCO minival Pix2seq (R50) box AP 42.6 #153 of 220 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