Methods › General › Attention Mechanisms › Neighborhood Attention

Neighborhood Attention

21 papers tagged archive 2025-07-28

Introduced by Ali Hassani et al. in Neighborhood Attention Transformer

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

Neighborhood Attention is a restricted self attention pattern in which each token's receptive field is limited to its nearest neighboring pixels. It was proposed in Neighborhood Attention Transformer as an alternative to other local attention mechanisms used in Hierarchical Vision Transformers.

NA is in concept similar to stand alone self attention (SASA), in that both can be implemented with a raster scan sliding window operation over the key value pair. However, NA would require a modification to handle corner pixels, which helps maintain a fixed receptive field size and an increased number of relative positions.

The primary challenge in experimenting with both NA and SASA has been computation. Simply extracting key values for each query is slow, takes up a large amount of memory, and is eventually intractable at scale. NA was therefore implemented through a new CUDA extension to PyTorch, NATTEN.

PaperSource

Papers archive 2025-07-28

21 shown of 21, 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 47 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 Segmentation7
Image Classification4
Decoder3
Image Segmentation3
Object Detection3
Segmentation3
image-classification3
Computational Efficiency2
Denoising2
Instance Segmentation2
Panoptic Segmentation2
SSIM2
3D Object Detection1
Autonomous Driving1
Classification1
Deblurring1
Depth Estimation1
Diagnostic1
Edge Detection1
Emotion Recognition1

Usage over time archive 2025-07-28

Papers per year tagged with Neighborhood Attention: 2022 to 2025, peak 6 6 0 2022: 6 papers 2022 2023: 5 papers 2023 2024: 6 papers 2024 2025: 4 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (21 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

Attention MechanismsAttention ModulesAttention Patterns

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