Methods › Computer Vision › Image Models › HaloNet
HaloNet
Introduced by Ashish Vaswani et al. in Scaling Local Self-Attention for Parameter Efficient Visual Backbones
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
A HaloNet is a self-attention based model for efficient image classification. It relies on a local self-attention architecture that efficiently maps to existing hardware with haloing. The formulation breaks translational equivariance, but the authors observe that it improves throughput and accuracies over the centered local self-attention used in regular self-attention. The approach also utilises a strided self-attentive downsampling operation for multi-scale feature extraction.
Papers archive 2025-07-28
2 shown of 2, 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.
-
HaloAE: An HaloNet based Local Transformer Auto-Encoder for Anomaly Detection and Localization 6 Aug 2022 · 0 repositories · arXiv:2208.03486
-
Scaling Local Self-Attention for Parameter Efficient Visual Backbones 23 Mar 2021 · 7 repositories · arXiv:2103.12731Syntology ran 12 of 20 samples · 8 unverified
Tasks archive 2025-07-28
9 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 |
|---|---|
| Anomaly Detection | 1 |
| Image Classification | 1 |
| Instance Segmentation | 1 |
| Object Detection | 1 |
| Segmentation | 1 |
| Semantic Segmentation | 1 |
| Transfer Learning | 1 |
| Unsupervised Anomaly Detection | 1 |
| object-detection | 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