Papers › Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions

Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions

24 Feb 2021ICCV 2021 10arXiv:2102.12122archive 2025-07-28

Wenhai Wang, Enze Xie, Xiang Li, Deng-Ping Fan, Kaitao Song, Ding Liang, Tong Lu, Ping Luo, Ling Shao

Although using convolutional neural networks (CNNs) as backbones achieves great successes in computer vision, this work investigates a simple backbone network useful for many dense prediction tasks without convolutions. Unlike the recently-proposed Transformer model (e.g., ViT) that is specially designed for image classification, we propose Pyramid Vision Transformer (PVT), which overcomes the difficulties of porting Transformer to various dense prediction tasks. PVT has several merits compared to prior arts. (1) Different from ViT that typically has low-resolution outputs and high computational and memory cost, PVT can be not only trained on dense partitions of the image to achieve high output resolution, which is important for dense predictions but also using a progressive shrinking pyramid to reduce computations of large feature maps. (2) PVT inherits the advantages from both CNN and Transformer, making it a unified backbone in various vision tasks without convolutions by simply replacing CNN backbones. (3) We validate PVT by conducting extensive experiments, showing that it boosts the performance of many downstream tasks, e.g., object detection, semantic, and instance segmentation. For example, with a comparable number of parameters, RetinaNet+PVT achieves 40.4 AP on the COCO dataset, surpassing RetinNet+ResNet50 (36.3 AP) by 4.1 absolute AP. We hope PVT could serve as an alternative and useful backbone for pixel-level predictions and facilitate future researches. Code is available at https://github.com/whai362/PVT.

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.

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

Code

Syntology 30 code samples harvested from 3 repositories linked to this paper: 22 ran (of which 16 constructed an object rather than computing a result; 18 with no instrument failure: 2 honoured, 0 violated, 16 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 4 samples from 1 repository, 4 ran (4 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 26 samples from 2 repositories, 18 ran (14 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 5 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

whai362/PVT officialmentioned in papermentioned on GitHubpytorchSyntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
DarshanDeshpande/jax-models mentioned on GitHubjaxSyntology: 7 samples, 5 ran (0 instrument-failed) · 2 unverified report
SforAiDl/vformer mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Vision Transformers for Dense Prediction (arXiv:2103.13413; that paper's own run record: 65 ran (of which 19 constructed an object rather than computing a result; 32 with no instrument failure: 0 honoured, 0 violated, 32 with no contract checked; 33 where Syntology's instrument failed) · 51 unverified) and ViViT: A Video Vision Transformer (arXiv:2103.15691; that paper's own run record: 14 ran (of which 10 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
hustvl/sparseinst mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Sparse Instance Activation for Real-Time Instance Segmentation (arXiv:2203.12827; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
martinsbruveris/tensorflow-image-models mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MLP-Mixer: An all-MLP Architecture for Vision (arXiv:2105.01601; that paper's own run record: 114 ran (of which 77 constructed an object rather than computing a result; 104 with no instrument failure: 2 honoured, 1 violated, 101 with no contract checked; 10 where Syntology's instrument failed) · 20 unverified); nothing checks that they implement this paper's method. report
microsoft/vision-longformer mentioned on GitHubpytorchSyntology: 19 samples, 13 ran (4 instrument-failed) · 6 unverified report
open-mmlab/mmpose mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RTMO: Towards High-Performance One-Stage Real-Time Multi-Person Pose Estimation (arXiv:2312.07526; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
wangermeng2021/PVT-tensorflow2 mentioned on GitHubtfSyntology: not harvested report
xiaohu2015/pvt_detectron2 mentioned on GitHubpytorchMITSyntology: not harvested report
open-mmlab/mmdetection pytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to An Open and Comprehensive Pipeline for Unified Object Grounding and Detection (arXiv:2401.02361; that paper's own run record: 4 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; 2 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
gitlab.com/birder/birder pytorchSyntology: not harvested 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

30 samples harvested: 22 ran (of which 16 constructed an object rather than computing a result; 18 with no instrument failure: 2 honoured, 0 violated, 16 with no contract checked; 4 where Syntology's instrument failed) · 8 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.

2ran · honoured contract
4ran · our draft was wrong
16ran
8unverified

Licence: 1 of the 30 samples is 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 3 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. 1 sample whose link to this paper records no repository is listed under one of this paper's own repositories, because identical code was harvested from it for another 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.

whai362/PVT official repository 4 samples, 4 ran (0 instrument-failed) · 0 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
classification/pvt.py ran Apache-2.0 (permissive) · 5dada1aeda7932eb · report fixture: returned Attention · level recorded 2026-09-22
Block in 252 papers
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
classification/pvt.py ran Apache-2.0 (permissive) · 583eadd9a5e6a087 · report fixture: returned Block · level recorded 2026-09-22
PatchEmbed in 123 papers
census: 9 implementations from 9 papers, 6 distinct outputs on one shared input
classification/pvt.py ran Apache-2.0 (permissive) · 916b4f73572180ec · report fixture: returned PatchEmbed · level recorded 2026-09-22
PyramidVisionTransformer classification/pvt.py ran Apache-2.0 (permissive) · c69b1b1a3052ca98 · report fixture: returned PyramidVisionTransformer · level recorded 2026-09-22
DarshanDeshpande/jax-models community (archive-listed) 7 samples, 5 ran (0 instrument-failed) · 2 unverified
AdaptiveAveragePool2D jax_models/models/pvit.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 4e79665da13fed0d · report fixture: returned AdaptiveAveragePool2D · level recorded 2026-09-22
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
jax_models/models/pvit.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 07fdb7e2bfa01afa · report fixture: returned Attention · level recorded 2026-09-22
DepthwiseConv2D in 8 papers jax_models/models/pvit.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · f523e66d872044ea · report fixture: returned DepthwiseConv2D · level recorded 2026-09-22
OverlapPatchEmbed in 16 papers jax_models/models/pvit.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · df41558bed765430 · report fixture: returned OverlapPatchEmbed · level recorded 2026-09-22
TransformerMLP in 5 papers jax_models/models/pvit.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 374179113e51b201 · report fixture: returned TransformerMLP · level recorded 2026-09-22
PyramidViT jax_models/models/pvit.py unverified Apache-2.0 (permissive) · 5fad6fb95a0d420f · report
microsoft/vision-longformer community (archive-listed) 19 samples, 13 ran (4 instrument-failed) · 6 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
src/models/msvit.py ran MIT (permissive) · 592e8438de425b53 · report fixture: returned Attention · level recorded 2026-09-22
FastAttention src/models/msvit.py ran MIT (permissive) · da55353e88022d26 · report fixture: returned FastAttention · level recorded 2026-09-22
LinformerSelfAttention src/models/msvit.py ran MIT (permissive) · 6ba11adb4f98f7ff · report fixture: returned LinformerSelfAttention · level recorded 2026-09-22
MlpBlock in 9 papers src/models/msvit.py ran MIT (permissive) · 0440cd3acf07c3c4 · report fixture: returned MlpBlock · level recorded 2026-09-22
PatchEmbed in 123 papers
census: 9 implementations from 9 papers, 6 distinct outputs on one shared input
src/models/msvit.py ran MIT (permissive) · b8071a3c02db7b92 · report fixture: returned PatchEmbed · level recorded 2026-09-22
SRSelfAttention src/models/msvit.py ran MIT (permissive) · e41b50defb828842 · report fixture: returned SRSelfAttention · level recorded 2026-09-22
SlidingChunk2D src/models/msvit.py ran MIT (permissive) · 46bc17ff8a5ba939 · report fixture: returned SlidingChunk2D · level recorded 2026-09-22
_get_invalid_locations_mask_cyclic src/models/msvit.py ran · our draft was wrong MIT (permissive) · 9e88f2b66f738494 · report fixture: signature nx:int/0/int, ny:int/0/int, padx:int/0/int, pady:int/0/int, w:int/0/int, device:str/0/str · returned tuple · level recorded 2026-09-22
_get_invalid_locations_mask_exact src/models/msvit.py ran · our draft was wrong MIT (permissive) · 813948d3f352d1c6 · report fixture: signature nx:int/0/int, ny:int/0/int, padx:int/0/int, pady:int/0/int, w:int/0/int, device:str/0/str · returned tuple · level recorded 2026-09-22
_get_invalid_locations_mask_zero src/models/msvit.py ran · our draft was wrong MIT (permissive) · f48afe5b9c50d66c · report fixture: signature nx:int/0/int, ny:int/0/int, padx:int/0/int, pady:int/0/int, w:int/0/int, device:str/0/str · returned tuple · level recorded 2026-09-22
gaussian_orthogonal_random_matrix in 6 papers src/models/msvit.py ran · honoured contract MIT (permissive) · 1652fbb1719cc1b4 · report fixture: signature nb_rows:int/0/int, nb_columns:int/0/int, scaling:int/0/int, device:NoneType/0/? · returned Tensor · level recorded 2026-09-22
init_ in 12 papers src/models/msvit.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · honoured contract fingerprinted licence of this copy not recorded · 3444251df88e6169 · report fixture: signature tensor:Tensor/2/float · returned Tensor · level recorded 2026-09-22
softmax_kernel in 7 papers src/models/msvit.py ran · our draft was wrong MIT (permissive) · 757aee54843af070 · report fixture: signature data:Tensor/4/float, projection_matrix:Tensor/2/float, is_query:bool/0/bool, normalize_data:bool/0/bool, eps:float/0/float, device:NoneType/0/? · returned Tensor · level recorded 2026-09-22
AttnBlock in 22 papers src/models/msvit.py unverified MIT (permissive) · 2de4320db751601f · report
Long2DSCSelfAttention src/models/msvit.py unverified MIT (permissive) · c7c2414a1044ea7d · report
MsViT src/models/msvit.py unverified MIT (permissive) · 380e07f5bfb682af · report
PerformerSelfAttention src/models/msvit.py unverified MIT (permissive) · 53e595a68e74e8a6 · report
mask_invalid_locations src/models/msvit.py unverified MIT (permissive) · b7a2d11b74ff36f6 · report
slidingchunk_2dautograd src/models/msvit.py unverified MIT (permissive) · 56b6ba9dcdd328f4 · 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. 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.

3 assemblies on this paper: 3 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

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

harvested Assembly for Pyramid Vision Transformer (graph method: Pyramid Vision Transformer). 8 bricks; individually on a fixture: 5 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; every one of the 5 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 3 siblings

  1. PyramidViT entry · level 0 · unverified · 5fad6fb95a0d420f
  2. Block model · level 0 · unverified · 3ec0d795856d98f3
  3. OverlapPatchEmbed model · level 1 · ran · df41558bed765430
  4. Attention model · level 1 · ran · 07fdb7e2bfa01afa
  5. DropPath helper · level 0 · unverified · 983cc65c35c3d898
  6. TransformerMLP helper · level 1 · ran · 374179113e51b201
  7. AdaptiveAveragePool2D helper · level 1 · ran · 4e79665da13fed0d
  8. DepthwiseConv2D helper · level 1 · ran · f523e66d872044ea

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

one of 3 siblings

  1. PyramidVisionTransformer entry · level 1 · ran · c69b1b1a3052ca98
  2. Block model · level 1 · ran · 583eadd9a5e6a087
  3. PatchEmbed model · level 1 · ran · 916b4f73572180ec
  4. Attention model · level 1 · ran · 5dada1aeda7932eb
  5. Mlp model · level 1 · ran · a1715055832f71fd

harvested Assembly for Pyramid Vision Transformer (graph method: Pyramid Vision Transformer). 26 bricks; individually on a fixture: 20 ran (of which 8 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 2 violated, 8 with no contract checked; 8 where Syntology's instrument failed) · 6 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. MsViT entry · level 0 · unverified · 380e07f5bfb682af
  2. AttnBlock model · level 0 · unverified · 2de4320db751601f
  3. FastAttention helper · level 1 · ran · da55353e88022d26
  4. Long2DSCSelfAttention helper · level 0 · unverified · c7c2414a1044ea7d
  5. MlpBlock model · level 1 · ran · 0440cd3acf07c3c4
  6. PatchEmbed model · level 1 · ran · b8071a3c02db7b92
  7. find_modules helper · level 1 · ran · our draft was wrong · 4e291c3ece372165
  8. get_module_device helper · level 1 · ran · our draft was wrong · f8ef5ca2539fcee5
  9. Attention model · level 1 · ran · 592e8438de425b53
  10. LinformerSelfAttention helper · level 1 · ran · 6ba11adb4f98f7ff
  11. PerformerSelfAttention helper · level 0 · unverified · 53e595a68e74e8a6
  12. SRSelfAttention helper · level 1 · ran · e41b50defb828842
  13. default helper · level 1 · ran · violated contract · 60fff7c3c400d7ff
  14. gaussian_orthogonal_random_matrix helper · level 1 · ran · honoured contract · 1652fbb1719cc1b4
  15. generalized_kernel helper · level 1 · ran · our draft was wrong · 3098ab3648cec16a
  16. linear_attention helper · level 1 · ran · our draft was wrong · 285e3997b7d7c24b
  17. softmax_kernel helper · level 1 · ran · our draft was wrong · 757aee54843af070
  18. mask_invalid_locations helper · level 0 · unverified · b7a2d11b74ff36f6
  19. slidingchunk_2dautograd helper · level 0 · unverified · 56b6ba9dcdd328f4
  20. Mlp model · level 1 · ran · 86db5e5160400425
  21. init_ helper · level 1 · ran · honoured contract · 3444251df88e6169
  22. exists helper · level 1 · ran · violated contract · aa5486a3650902d8
  23. _get_invalid_locations_mask_cyclic helper · level 1 · ran · our draft was wrong · 9e88f2b66f738494
  24. _get_invalid_locations_mask_exact helper · level 1 · ran · our draft was wrong · 813948d3f352d1c6
  25. _get_invalid_locations_mask_zero helper · level 1 · ran · our draft was wrong · f48afe5b9c50d66c
  26. SlidingChunk2D helper · level 1 · ran · 46bc17ff8a5ba939

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="2102.12122") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image ClassificationInstance SegmentationObject DetectionSemantic Segmentationimage-classificationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection COCO minival PVT-Large (RetinaNet 3x,MS) AP50 63.6 #140 of 220 Archive leaderboard report
Object Detection COCO minival PVT-Large (RetinaNet 3x,MS) AP75 46.1 #140 of 220 Archive leaderboard report
Object Detection COCO minival PVT-Large (RetinaNet 3x,MS) APL 59.5 #140 of 220 Archive leaderboard report
Object Detection COCO minival PVT-Large (RetinaNet 3x,MS) APM 46.0 #140 of 220 Archive leaderboard report
Object Detection COCO minival PVT-Large (RetinaNet 3x,MS) APS 26.1 #140 of 220 Archive leaderboard report
Object Detection COCO minival PVT-Large (RetinaNet 3x,MS) box AP 43.4 #140 of 220 Archive leaderboard report
Object Detection COCO minival PVT-Large (RetinaNet 1x) AP50 63.7 #151 of 220 Archive leaderboard report
Object Detection COCO minival PVT-Large (RetinaNet 1x) AP75 45.4 #151 of 220 Archive leaderboard report
Object Detection COCO minival PVT-Large (RetinaNet 1x) APL 58.4 #151 of 220 Archive leaderboard report
Object Detection COCO minival PVT-Large (RetinaNet 1x) APM 46.0 #151 of 220 Archive leaderboard report
Object Detection COCO minival PVT-Large (RetinaNet 1x) APS 25.8 #151 of 220 Archive leaderboard report
Object Detection COCO minival PVT-Large (RetinaNet 1x) box AP 42.6 #151 of 220 Archive leaderboard report
Semantic Segmentation DensePASS PVT (Tiny, FPN) mIoU 31.20% #26 of 36 Archive leaderboard report
Semantic Segmentation SynPASS PVT mIoU 32.68% #4 of 6 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

Introduced by this paper: Spatial-Reduction Attention

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPVTPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxSpatial-Reduction AttentionTransformer

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