Methods › General › Attention Modules › Spatially Separable Self-Attention
Spatially Separable Self-Attention
Introduced by Xiangxiang Chu et al. in Twins: Revisiting the Design of Spatial Attention in Vision Transformers
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Spatially Separable Self-Attention, or SSSA, is an attention module used in the Twins-SVT architecture that aims to reduce the computational complexity of vision transformers for dense prediction tasks (given high-resolution inputs). SSSA is composed of locally-grouped self-attention (LSA) and global sub-sampled attention (GSA).
Formally, spatially separable self-attention (SSSA) can be written as:
ẑ_(i j)ˡ= LSA ( LayerNorm (z_(i j)ˡ⁻¹))+z_(i j)ˡ⁻¹
z_(i j)ˡ=FFN(LayerNorm(ẑ_(i j)ˡ))+ẑ_(i j)ˡ
ẑˡ⁺¹= GSA ( LayerNorm (zˡ))+zˡ
zˡ⁺¹= FFN ( LayerNorm (ẑˡ⁺¹))+ẑˡ⁺¹
i ∈{1,2, …., m}, j ∈{1,2, …., n}
where LSA means locally-grouped self-attention within a sub-window; GSA is the global sub-sampled attention by interacting with the representative keys (generated by the sub-sampling functions) from each sub-window ẑ_(i j) ∈ℛ^(k₁ ×k₂ ×C) . Both LSA and GSA have multiple heads as in the standard self-attention.
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: self-modulating attention; Orthogonal Self-Attention; Omni Self-Attention (OSA); Local Self-Attention Block; Hierarchical Self-Attention; Self-Gating Attention (SGA); Grouped Self-Attention (GSA); Dualway Self Attention (DWSA).
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: 2 · with a code link: 1 · where Syntology ran a sample: 1 (0 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 (1 of 2 tagged: 0 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 2 of 2, 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.
-
Logically at Factify 2: A Multi-Modal Fact Checking System Based on Evidence Retrieval techniques and Transformer Encoder Architecture 9 Jan 2023 · 0 repositories · arXiv:2301.03127
-
Twins: Revisiting the Design of Spatial Attention in Vision Transformers 28 Apr 2021 · 9 repositories · arXiv:2104.13840Syntology official (archive's flag): 2 ran · 2 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; 2 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)
Tasks archive 2025-07-28
7 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 |
|---|---|
| Avg | 1 |
| Benchmarking | 1 |
| Fact Checking | 1 |
| Fact Verification | 1 |
| Image Classification | 1 |
| Retrieval | 1 |
| Semantic Segmentation | 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