Methods › General › Attention Mechanisms › FcaNet
Frequency channel attention networks
FcaNet
Introduced by Zequn Qin et al. in FcaNet: Frequency Channel Attention Networks
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
FCANet contains a novel multi-spectral channel attention module. Given an input feature map X ∈ℝ^(C ×H ×W), multi-spectral channel attention first splits X into many parts xⁱ ∈ℝ^(C′ ×H ×W). Then it applies a 2D DCT to each part xⁱ. Note that a 2D DCT can use pre-processing results to reduce computation. After processing each part, all results are concatenated into a vector. Finally, fully connected layers, ReLU activation and a sigmoid are used to get the attention vector as in an SE block. This can be formulated as: s = F_(fca)(X, θ) = σ(W₂ δ(W₁[(DCT(Group(X)))])) Y = s X where Group(·) indicates dividing the input into many groups and DCT(·) is the 2D discrete cosine transform.
This work based on information compression and discrete cosine transforms achieves excellent performance on the classification task.
In Syntology name not resolved (unknown_name). Other entries in Syntology's graph carry this name; the lookup's note below says what that means for this name.
From the lookup's note on this name: Nothing resolved to this name, but 2 entries in Syntology's graph carry it; the most cited is the paper “FcaNet: Frequency Channel Attention Networks” (arXiv:2012.11879, 1,196 citations). The lookup reads this as a miss of its own name matching, not a gap in coverage: the graph holds the name under a spelling the lookup did not reach. For arXiv:2012.11879: its page on this site · ask the lookup about it.
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: 2 · where Syntology ran a sample: 0 (0 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran: none of the 2 tagged papers has a Syntology run on record
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.
-
OrthoNets: Orthogonal Channel Attention Networks 6 Nov 2023 · 1 repository · arXiv:2311.03071
-
FcaNet: Frequency Channel Attention Networks 22 Dec 2020 · 7 repositories · arXiv:2012.11879
Tasks archive 2025-07-28
6 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 | 1 |
| Instance Segmentation | 1 |
| Object Detection | 1 |
| Semantic Segmentation | 1 |
| image-classification | 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