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.

Paper PDF Code

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

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

whai362/PVT officialmentioned in papermentioned on GitHubpytorch report

Owais-Ansari/Unet3plus mentioned on GitHubpytorch report

martinsbruveris/tensorflow-image-models mentioned on GitHubtf report

open-mmlab/mmpose mentioned on GitHubpytorchApache-2.0 report

rwightman/pytorch-image-models mentioned on GitHubpytorch report

sithu31296/semantic-segmentation mentioned on GitHubpytorch report

xiaohu2015/pvt_detectron2 mentioned on GitHubpytorchMIT report

BR-IDL/PaddleViT paddle report

MS-Mind/MS-Code-02 mindspore report

Mind23-2/MindCode-110 mindspore report

PaddlePaddle/PaddleClas paddleApache-2.0 report

justld/PVTV2_paddle paddle report

leondgarse/keras_cv_attention_models tf report

mindspore-courses/External-Attention-MindSpore mindspore report

open-mmlab/mmdetection pytorchApache-2.0 report

shinya7y/UniverseNet pytorchApache-2.0 report

gitlab.com/birder/birder pytorch 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

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

Tasks

Image Classification Object Detection Panoptic Segmentation

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
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 Encodings Adam Attention BPE Dense Connections Depthwise Convolution Dropout Label Smoothing Layer Normalization Linear Layer Multi-Head Attention PVTv2 Position-Wise Feed-Forward Layer Residual Connection Softmax Stochastic Depth Swin Transformer Transformer Vision 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