Methods › Computer Vision › Image Models › PVTv2
Pyramid Vision Transformer v2
PVTv2
Introduced by Wenhai Wang et al. in PVT v2: Improved Baselines with Pyramid Vision Transformer
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Pyramid Vision Transformer v2 (PVTv2) is a type of Vision Transformer for detection and segmentation tasks. It improves on PVTv1 through several design improvements: (1) overlapping patch embedding, (2) convolutional feed-forward networks, and (3) linear complexity attention layers that are orthogonal to the PVTv1 framework.
Papers archive 2025-07-28
4 shown of 4, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Improving existing segmentators performance with zero-shot segmentators 26 Jul 2023 · 1 repository
-
Locality Guidance for Improving Vision Transformers on Tiny Datasets 20 Jul 2022 · 1 repository · arXiv:2207.10026Syntology ran 0 of 1 samples · 1 unverified
-
PVT-COV19D: Pyramid Vision Transformer for COVID-19 Diagnosis 30 Jun 2022 · 0 repositories · arXiv:2206.15069
-
PVT v2: Improved Baselines with Pyramid Vision Transformer 25 Jun 2021 · 18 repositories · arXiv:2106.13797
Tasks archive 2025-07-28
7 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| COVID-19 Diagnosis | 1 |
| Camouflaged Object Segmentation | 1 |
| Image Classification | 1 |
| Object Detection | 1 |
| Panoptic Segmentation | 1 |
| Segmentation | 1 |
| Zero-shot Generalization | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
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