Methods › Computer Vision › Feature Pyramid Blocks › ASFF

Adaptively Spatial Feature Fusion

ASFF

1 paper tagged archive 2025-07-28

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

ASFF, or Adaptively Spatial Feature Fusion, is a method for pyramidal feature fusion. It learns the way to spatially filter conflictive information to suppress inconsistency across different feature scales, thus improving the scale-invariance of features.

ASFF enables the network to directly learn how to spatially filter features at other levels so that only useful information is kept for combination. For the features at a certain level, features of other levels are first integrated and resized into the same resolution and then trained to find the optimal fusion. At each spatial location, features at different levels are fused adaptively, i.e., some features may be filter out as they carry contradictory information at this location and some may dominate with more discriminative clues. ASFF offers several advantages: (1) as the operation of searching the optimal fusion is differential, it can be conveniently learned in back-propagation; (2) it is agnostic to the backbone model and it is applied to single-shot detectors that have a feature pyramid structure; and (3) its implementation is simple and the increased computational cost is marginal.

Let xᵢⱼ^(n→l) denote the feature vector at the position (i,j) on the feature maps resized from level n to level l. Following a feature resizing stage, we fuse the features at the corresponding level l as follows:

yᵢⱼˡ = αˡᵢⱼ ·xᵢⱼ^(1→l) + βˡᵢⱼ ·xᵢⱼ^(2→l) +γˡᵢⱼ ·xᵢⱼ^(3→l),

where yᵢⱼˡ implies the (i,j)-th vector of the output feature maps yˡ among channels. αˡᵢⱼ, βˡᵢⱼ and γˡᵢⱼ refer to the spatial importance weights for the feature maps at three different levels to level l, which are adaptively learned by the network. Note that αˡᵢⱼ, βˡᵢⱼ and γˡᵢⱼ can be simple scalar variables, which are shared across all the channels. Inspired by acnet, we force αˡᵢⱼ+βˡᵢⱼ+γˡᵢⱼ=1 and αˡᵢⱼ,βˡᵢⱼ,γˡᵢⱼ ∈[0,1], and

αˡᵢⱼ = (e^(λˡ_(αᵢⱼ)))/(e^(λˡ_(αᵢⱼ)) + e^(λˡ_(βᵢⱼ)) + e^(λˡ_(γᵢⱼ))).

Here αˡᵢⱼ, βˡᵢⱼ and γˡᵢⱼ are defined by using the softmax function with λˡ_(αᵢⱼ), λˡ_(βᵢⱼ) and λˡ_(γᵢⱼ) as control parameters respectively. We use 1×1 convolution layers to compute the weight scalar maps λˡ_α, λˡᵦ and λˡᵧ from x^(1→l), x^(2→l) and x^(3→l) respectively, and they can thus be learned through standard back-propagation.

With this method, the features at all the levels are adaptively aggregated at each scale. The outputs are used for object detection following the same pipeline of YOLOv3.

Source: Learning Spatial Fusion for Single-Shot Object DetectionSee Code · ruinmessi/ASFF

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: 1 · with a code link: 1 · 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 1 tagged papers has a Syntology run on record

Page 1 of 1: paper 1 of 1, 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

3 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
Object1
Object Detection1
object-detection1

Usage over time archive 2025-07-28

Papers per year tagged with ASFF: 2019 to 2019, peak 1 1 0 2019: 1 paper 2019
Papers per year the archive tags with this method, by the paper's archive date (1 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

Feature Pyramid 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