Methods › Computer Vision › Vision Transformers › Focal Transformers
Focal Transformers
Introduced by Jianwei Yang et al. in Focal Self-attention for Local-Global Interactions in Vision Transformers
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
The focal self-attention is built to make Transformer layers scalable to high-resolution inputs. Instead of attending all tokens at fine-grain, the approach attends the fine-grain tokens only locally, but the summarized ones globally. As such, it can cover as many regions as standard self-attention but with much less cost. An image is first partitioned into patches, resulting in visual tokens. Then a patch embedding layer, consisting of a convolutional layer with filter and stride of same size, to project the patches into hidden features. This spatial feature map in then passed to four stages of focal Transformer blocks. Each focal Transformer block consists of Nᵢ focal Transformer layers. Patch embedding layers are used in between to reduce spatial size of feature map by factor 2, while feature dimension increased by 2.
In Syntology name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.
Near matches the lookup lists, each a different name: FoCal; FOCAL; RL-Focal; CKA-focal; Focal Reward; Focal Guidance; Anti-Focal loss; Focal Rewriting.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
Papers archive 2025-07-28
archive papers tagged: 4 · with a code link: 4 · where Syntology ran a sample: 2 (1 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (2 of 4 tagged: 1 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 4 of 4, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
Explicitly Increasing Input Information Density for Vision Transformers on Small Datasets 25 Oct 2022 · 1 repository · arXiv:2210.14319Syntology official (archive's flag): 4 ran · 4 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified (of 7 harvested samples) · 7 pointer-only (licence)
-
Focal-WNet: An Architecture Unifying Convolution and Attention for Depth Estimation 18 Jul 2022 · 1 repository
-
Focal Attention for Long-Range Interactions in Vision Transformers 1 Dec 2021 · 1 repository
-
Focal Self-attention for Local-Global Interactions in Vision Transformers 1 Jul 2021 · 3 repositories · arXiv:2107.00641Syntology official (archive's flag): 1 ran · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 2 pointer-only (licence)
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 |
|---|---|
| Image Classification | 2 |
| Object Detection | 2 |
| Semantic Segmentation | 2 |
| image-classification | 2 |
| object-detection | 2 |
| Decoder | 1 |
| Depth Estimation | 1 |
| Instance Segmentation | 1 |
| Monocular Depth Estimation | 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