Methods › General › Position Embeddings › Conditional Positional Encoding
Conditional Positional Encoding
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.
Conditional Positional Encoding, or CPE, is a type of positional encoding for vision transformers. Unlike previous fixed or learnable positional encodings, which are predefined and independent of input tokens, CPE is dynamically generated and conditioned on the local neighborhood of the input tokens. As a result, CPE aims to generalize to the input sequences that are longer than what the model has ever seen during training. CPE can also keep the desired translation-invariance in the image classification task. CPE can be implemented with a Position Encoding Generator (PEG) and incorporated into the current Transformer framework.
Papers archive 2025-07-28
7 shown of 7, 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.
-
WriteViT: Handwritten Text Generation with Vision Transformer 19 May 2025 · 1 repository · arXiv:2505.13235
-
CBraMod: A Criss-Cross Brain Foundation Model for EEG Decoding 10 Dec 2024 · 1 repository · arXiv:2412.07236Syntology ran 2 of 5 samples · 3 unverified
-
Serialized Point Mamba: A Serialized Point Cloud Mamba Segmentation Model 17 Jul 2024 · 0 repositories · arXiv:2407.12319
-
Heracles: A Hybrid SSM-Transformer Model for High-Resolution Image and Time-Series Analysis 26 Mar 2024 · 2 repositories · arXiv:2403.18063Syntology ran 4 of 4 samples · 0 unverified · 4 pointer-only (licence)
-
V4d: voxel for 4d novel view synthesis 28 May 2022 · 1 repository · arXiv:2205.14332
-
Twins: Revisiting the Design of Spatial Attention in Vision Transformers 28 Apr 2021 · 9 repositories · arXiv:2104.13840Syntology ran 0 of 2 samples · 2 unverified · 2 pointer-only (licence)
-
Conditional Positional Encodings for Vision Transformers 22 Feb 2021 · 2 repositories · arXiv:2102.10882
Tasks archive 2025-07-28
20 shown of 27 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
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