Methods › Computer Vision › Feature Extractors › FSAF
FSAF
Introduced by Chenchen Zhu et al. in Feature Selective Anchor-Free Module for Single-Shot Object Detection
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
FSAF, or Feature Selective Anchor-Free, is a building block for single-shot object detectors. It can be plugged into single-shot detectors with feature pyramid structure. The FSAF module addresses two limitations brought up by the conventional anchor-based detection: 1) heuristic-guided feature selection; 2) overlap-based anchor sampling. The general concept of the FSAF module is online feature selection applied to the training of multi-level anchor-free branches. Specifically, an anchor-free branch is attached to each level of the feature pyramid, allowing box encoding and decoding in the anchor-free manner at an arbitrary level. During training, we dynamically assign each instance to the most suitable feature level. At the time of inference, the FSAF module can work jointly with anchor-based branches by outputting predictions in parallel. We instantiate this concept with simple implementations of anchor-free branches and online feature selection strategy
The general concept is presented in the Figure to the right. An anchor-free branch is built per level of feature pyramid, independent to the anchor-based branch. Similar to the anchor-based branch, it consists of a classification subnet and a regression subnet (not shown in figure). An instance can be assigned to arbitrary level of the anchor-free branch. During training, we dynamically select the most suitable level of feature for each instance based on the instance content instead of just the size of instance box. The selected level of feature then learns to detect the assigned instances. At inference, the FSAF module can run independently or jointly with anchor-based branches. The FSAF module is agnostic to the backbone network and can be applied to single-shot detectors with a structure of feature pyramid. Additionally, the instantiation of anchor-free branches and online feature selection can be various.
Papers archive 2025-07-28
7 shown of 7, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
FAD-SAR: A Novel Fishing Activity Detection System via Synthetic Aperture Radar Images Based on Deep Learning Method 28 Apr 2024 · 0 repositories · arXiv:2404.18245
-
Deep learning approaches to building rooftop thermal bridge detection from aerial images 12 Dec 2022 · 1 repository
-
Lost in Compression: the Impact of Lossy Image Compression on Variable Size Object Detection within Infrared Imagery 16 May 2022 · 0 repositories · arXiv:2205.08002
-
Fracture Detection in Wrist X-ray Images Using Deep Learning-Based Object Detection Models 14 Nov 2021 · 0 repositories · arXiv:2111.07355
-
Reinforced Few-Shot Acquisition Function Learning for Bayesian Optimization 8 Jun 2021 · 0 repositories · arXiv:2106.04335
-
AGSFCOS: Based on attention mechanism and Scale-Equalizing pyramid network of object detection 20 May 2021 · 0 repositories · arXiv:2105.09596
-
Feature Selective Anchor-Free Module for Single-Shot Object Detection 2 Mar 2019 · 4 repositories · arXiv:1903.00621Syntology ran 0 of 8 samples · 8 unverified
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.
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