Methods › Computer Vision › Feature Extractors › SFAM
Scale-wise Feature Aggregation Module
SFAM
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
SFAM, or Scale-wise Feature Aggregation Module, is a feature extraction block from the M2Det architecture. It aims to aggregate the multi-level multi-scale features generated by Thinned U-Shaped Modules into a multi-level feature pyramid.
The first stage of SFAM is to concatenate features of the equivalent scale together along the channel dimension. The aggregated feature pyramid can be presented as X =[X₁,X₂,…,Xᵢ], where Xᵢ = Concat(xᵢ¹,xᵢ²,…,xᵢᴸ) ∈ℝ^(Wᵢ×Hᵢ×C) refers to the features of the i-th largest scale. Here, each scale in the aggregated pyramid contains features from multi-level depths.
However, simple concatenation operations are not adaptive enough. In the second stage, we introduce a channel-wise attention module to encourage features to focus on channels that they benefit most. Following Squeeze-and-Excitation, we use global average pooling to generate channel-wise statistics z ∈ℝ^C at the squeeze step. And to fully capture channel-wise dependencies, the following excitation step learns the attention mechanism via two fully connected layers:
s = Fₑₓ(z,W) = σ(W₂ δ(W₁z)),
where σ refers to the ReLU function, δ refers to the sigmoid function, W₁ ∈ℝ^(C/r×C) , W₂ ∈ℝ^(C×C/r), r is the reduction ratio (r=16 in our experiments). The final output is obtained by reweighting the input X with activation s:
X̃ᵢᶜ = F_(scale)(Xᵢᶜ,s_c) = s_c ·Xᵢᶜ,
where X̃ᵢ̃ = [X̃ᵢ¹,X̃ᵢ²,...,X̃ᵢ^C], each of the features is enhanced or weakened by the rescaling operation.
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.
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: 5 · with a code link: 3 · where Syntology ran a sample: 1 (1 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 (1 of 5 tagged: 1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 5 of 5, 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.
-
Emphasizing Crucial Features for Efficient Image Restoration 19 May 2024 · 1 repository · arXiv:2405.11468
-
Towards Robust Visual Information Extraction in Real World: New Dataset and Novel Solution 24 Jan 2021 · 1 repository · arXiv:2102.06732
-
Structure from Articulated Motion: Accurate and Stable Monocular 3D Reconstruction without Training Data 12 May 2019 · 0 repositories · arXiv:1905.04789
-
Adversarial Learning-Based On-Line Anomaly Monitoring for Assured Autonomy 12 Nov 2018 · 0 repositories · arXiv:1811.04539
-
M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network 12 Nov 2018 · 11 repositories · arXiv:1811.04533Syntology 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
Tasks archive 2025-07-28
13 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 |
|---|---|
| 3D Feature Matching | 1 |
| 3D Reconstruction | 1 |
| Anomaly Detection | 1 |
| Decoder | 1 |
| Generative Adversarial Network | 1 |
| Image Restoration | 1 |
| Object | 1 |
| Object Detection | 1 |
| Text Detection | 1 |
| Text Spotting | 1 |
| Video Prediction | 1 |
| document understanding | 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