Papers › PVT v2: Improved Baselines with Pyramid Vision Transformer

PVT v2: Improved Baselines with Pyramid Vision Transformer

25 Jun 2021arXiv:2106.13797archive 2025-07-28

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

Transformer recently has presented encouraging progress in computer vision. In this work, we present new baselines by improving the original Pyramid Vision Transformer (PVT v1) by adding three designs, including (1) linear complexity attention layer, (2) overlapping patch embedding, and (3) convolutional feed-forward network. With these modifications, PVT v2 reduces the computational complexity of PVT v1 to linear and achieves significant improvements on fundamental vision tasks such as classification, detection, and segmentation. Notably, the proposed PVT v2 achieves comparable or better performances than recent works such as Swin Transformer. We hope this work will facilitate state-of-the-art Transformer researches in computer vision. Code is available at https://github.com/whai362/PVT.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page 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

18 repositories listed; official and paper-mentioned ones first.

whai362/PVT officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions (arXiv:2102.12122; that paper's own run record: 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); nothing checks that they implement this paper's method. report
Owais-Ansari/Unet3plus mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to U-Net: Convolutional Networks for Biomedical Image Segmentation (arXiv:1505.04597; that paper's own run record: 530 ran (of which 247 constructed an object rather than computing a result; 378 with no instrument failure: 18 honoured, 10 violated, 350 with no contract checked; 152 where Syntology's instrument failed) · 227 unverified), UNet 3+: A Full-Scale Connected UNet for Medical Image Segmentation (arXiv:2004.08790; that paper's own run record: 9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified) and A ConvNet for the 2020s (arXiv:2201.03545; that paper's own run record: 57 ran (of which 39 constructed an object rather than computing a result; 49 with no instrument failure: 2 honoured, 0 violated, 47 with no contract checked; 8 where Syntology's instrument failed) · 23 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
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
rwightman/pytorch-image-models mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdamP: Slowing Down the Slowdown for Momentum Optimizers on Scale-invariant Weights (arXiv:2006.08217; that paper's own run record: 4 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
sithu31296/semantic-segmentation mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers (arXiv:2105.15203; that paper's own run record: 66 ran (of which 22 constructed an object rather than computing a result; 52 with no instrument failure: 1 honoured, 2 violated, 49 with no contract checked; 14 where Syntology's instrument failed) · 20 unverified), FaPN: Feature-aligned Pyramid Network for Dense Image Prediction (arXiv:2108.07058; that paper's own run record: 2 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; 0 where Syntology's instrument failed) · 2 unverified) and A ConvNet for the 2020s (arXiv:2201.03545; that paper's own run record: 57 ran (of which 39 constructed an object rather than computing a result; 49 with no instrument failure: 2 honoured, 0 violated, 47 with no contract checked; 8 where Syntology's instrument failed) · 23 unverified); nothing checks that they implement this paper's method. report
xiaohu2015/pvt_detectron2 mentioned on GitHubpytorchMITSyntology: not harvested report
BR-IDL/PaddleViT paddleSyntology: not harvested report
MS-Mind/MS-Code-02 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications (arXiv:2206.10589; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
MS-Mind/MS-Code-02 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications (arXiv:2206.10589; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
Mind23-2/MindCode-110 mindsporeSyntology: not harvested report
PaddlePaddle/PaddleClas paddleApache-2.0Syntology: not harvested report
justld/PVTV2_paddle paddleSyntology: not harvested report
leondgarse/keras_cv_attention_models tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RepViT: Revisiting Mobile CNN From ViT Perspective (arXiv:2307.09283; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
mindspore-courses/External-Attention-MindSpore mindsporeSyntology: 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
shinya7y/UniverseNet pytorchApache-2.0Syntology: not harvested 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image ClassificationObject DetectionPanoptic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet PVTv2-B4 GFLOPs 11.8 #391 of 1060 Archive leaderboard report
Image Classification ImageNet PVTv2-B4 Number of params 82M #391 of 1060 Archive leaderboard report
Image Classification ImageNet PVTv2-B4 Top 1 Accuracy 83.8% #391 of 1060 Archive leaderboard report
Image Classification ImageNet PVTv2-B3 GFLOPs 6.9 #457 of 1060 Archive leaderboard report
Image Classification ImageNet PVTv2-B3 Number of params 45.2M #457 of 1060 Archive leaderboard report
Image Classification ImageNet PVTv2-B3 Top 1 Accuracy 83.2% #457 of 1060 Archive leaderboard report
Image Classification ImageNet PVTv2-B2 GFLOPs 4 #585 of 1060 Archive leaderboard report
Image Classification ImageNet PVTv2-B2 Number of params 25.4M #585 of 1060 Archive leaderboard report
Image Classification ImageNet PVTv2-B2 Top 1 Accuracy 82% #585 of 1060 Archive leaderboard report
Image Classification ImageNet PVTv2-B1 GFLOPs 2.1 #813 of 1060 Archive leaderboard report
Image Classification ImageNet PVTv2-B1 Number of params 13.1M #813 of 1060 Archive leaderboard report
Image Classification ImageNet PVTv2-B1 Top 1 Accuracy 78.7% #813 of 1060 Archive leaderboard report
Image Classification ImageNet PVTv2-B0 GFLOPs 0.6 #1021 of 1060 Archive leaderboard report
Image Classification ImageNet PVTv2-B0 Number of params 3.4M #1021 of 1060 Archive leaderboard report
Image Classification ImageNet PVTv2-B0 Top 1 Accuracy 70.5% #1021 of 1060 Archive leaderboard report
Object Detection COCO minival Sparse R-CNN (PVTv2-B2) AP50 69.5 #80 of 220 Archive leaderboard report
Object Detection COCO minival Sparse R-CNN (PVTv2-B2) AP75 54.9 #80 of 220 Archive leaderboard report
Object Detection COCO minival Sparse R-CNN (PVTv2-B2) box AP 50.1 #80 of 220 Archive leaderboard report
Object Detection COCO-O PVTv2-B5 (Mask R-CNN) Average mAP 28.2 #23 of 45 Archive leaderboard report
Object Detection COCO-O PVTv2-B5 (Mask R-CNN) Effective Robustness 6.85 #23 of 45 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: PVTv2

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDepthwise ConvolutionDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPVTv2Position-Wise Feed-Forward LayerResidual ConnectionSoftmaxStochastic DepthSwin TransformerTransformerVision Transformer

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