Methods › General › Miscellaneous Components › Positional Encoding Generator

Positional Encoding Generator

8 papers tagged archive 2025-07-28

Introduced by Xiangxiang Chu et al. in Conditional Positional Encodings for Vision Transformers

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

Positional Encoding Generator, or PEG, is a module used in the Conditional Position Encoding position embeddings. It dynamically produce the positional encodings conditioned on the local neighborhood of an input token. To condition on the local neighbors, we first reshape the flattened input sequence X ∈ℝ^(B ×N ×C) of DeiT back to X^' ∈ℝ^(B ×H ×W ×C) in the 2 -D image space. Then, a function (denoted by ℱ in the Figure) is repeatedly applied to the local patch in X^' to produce the conditional positional encodings E^(B ×H ×W ×C) . PEG can be efficiently implemented with a 2-D convolution with kernel k(k ≥3) and (k-1)/2 zero paddings. Note that the zero paddings here are important to make the model be aware of the absolute positions, and ℱ can be of various forms such as separable convolutions and many others.

PaperSource

Papers archive 2025-07-28

8 shown of 8, 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.

Tasks archive 2025-07-28

20 shown of 29 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Semantic Segmentation3
Image Classification2
Instance Segmentation2
Mamba2
3D Instance Segmentation1
3D Reconstruction1
3D Semantic Segmentation1
AutoML1
Classification1
Computational Efficiency1
EEG1
Eeg Decoding1
General Classification1
Handwriting generation1
Inductive Bias1
LIDAR Semantic Segmentation1
Novel View Synthesis1
Point Cloud Segmentation1
Position1
Segmentation1

Usage over time archive 2025-07-28

Papers per year tagged with Positional Encoding Generator: 2021 to 2025, peak 4 4 0 2021: 2 papers 2021 2022: 1 paper 2022 2023: 0 papers 2023 2024: 4 papers 2024 2025: 1 paper 2025
Papers per year the archive tags with this method, by the paper's archive date (8 dated). Bars are counts, not a trend claim.

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

Miscellaneous Components

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