Methods › Computer Vision › Image Model Blocks › Scale Aggregation Block

Scale Aggregation Block

7 papers tagged archive 2025-07-28

Introduced by Yi Li et al. in Data-Driven Neuron Allocation for Scale Aggregation Networks

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

A Scale Aggregation Block concatenates feature maps at a wide range of scales. Feature maps for each scale are generated by a stack of downsampling, convolution and upsampling operations. The proposed scale aggregation block is a standard computational module which readily replaces any given transformation Y=T(X), where X∈ℝ^(H×W×C), Y∈ℝ^(H×W×Cₒ) with C and Cₒ being the input and output channel number respectively. T is any operator such as a convolution layer or a series of convolution layers. Assume we have L scales. Each scale l is generated by sequentially conducting a downsampling Dₗ, a transformation Tₗ and an unsampling operator Uₗ:

X^’ₗ=Dₗ(X),

Y^’ₗ=Tₗ(X^’ₗ),

Yₗ=Uₗ(Y^’ₗ),

where X^’ₗ∈ℝ^(Hₗ×Wₗ×C), Y^’ₗ∈ℝ^(Hₗ×Wₗ×Cₗ), and Yₗ∈ℝ^(H×W×Cₗ). Notably, Tₗ has the similar structure as T. We can concatenate all L scales together, getting

Y^’=‖ᴸ₁Uₗ(Tₗ(Dₗ(X))),

where ‖ indicates concatenating feature maps along the channel dimension, and Y^’ ∈ℝ^(H×W×∑ᴸ₁ Cₗ) is the final output feature maps of the scale aggregation block.

In the reference implementation, the downsampling Dₗ with factor s is implemented by a max pool layer with s×s kernel size and s stride. The upsampling Uₗ is implemented by resizing with the nearest neighbor interpolation.

PaperSourceSee Code · Eli-YiLi/ScaleNet

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: Cascaded Scale Aggregation layer; Scale-Aware Aggregation (SAA) module; Multi-scale Affinity Aggregation (MAA); Multi-Scale Dynamic Aggregation (MSDA) module; Adaptive Multi-Scale Goodness Aggregation (AMSGA); Accelerated Multi-Scale Aggregation network (AMSA); TensorRT plugin for Multi-Scale Deformable Aggregation (MSDA); SCALE.

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: 7 · with a code link: 5 · 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 7 tagged papers has a Syntology run on record

Page 1 of 1: papers 1 to 7 of 7, 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.

Tasks archive 2025-07-28

18 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Graph Learning2
Image Classification2
Node Classification2
Pose Estimation2
3D Reconstruction1
Camera Pose Estimation1
Classification1
Geometric Matching1
Multi-Person Pose Estimation1
Neural Architecture Search1
Node Classification on Non-Homophilic (Heterophilic) Graphs1
Object Detection1
One-Shot Learning1
Representation Learning1
Semantic Segmentation1
image-classification1
model1
object-detection1

Usage over time archive 2025-07-28

Papers per year tagged with Scale Aggregation Block: 2019 to 2024, peak 2 2 0 2019: 1 paper 2019 2020: 1 paper 2020 2021: 1 paper 2021 2022: 1 paper 2022 2023: 1 paper 2023 2024: 2 papers 2024
Papers per year the archive tags with this method, by the paper's archive date (7 dated). Bars are counts, not a trend claim.

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

Image Model Blocks

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