Papers › Feature Selective Anchor-Free Module for Single-Shot Object Detection

Feature Selective Anchor-Free Module for Single-Shot Object Detection

2 Mar 2019CVPR 2019 6arXiv:1903.00621archive 2025-07-28

Chenchen Zhu, Yihui He, Marios Savvides

We motivate and present feature selective anchor-free (FSAF) module, a simple and effective 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. Experimental results on the COCO detection track show that our FSAF module performs better than anchor-based counterparts while being faster. When working jointly with anchor-based branches, the FSAF module robustly improves the baseline RetinaNet by a large margin under various settings, while introducing nearly free inference overhead. And the resulting best model can achieve a state-of-the-art 44.6% mAP, outperforming all existing single-shot detectors on COCO.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1903.00621")

Code

Syntology Ran 0 of 8 code samples harvested from 1 repository linked to this paper; 8 have no recorded run.

By repository: community (archive-listed): 8 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

xuannianz/FSAF mentioned on GitHubtf report
open-mmlab/mmdetection pytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

8 samples harvested; 0 ran; 0 honoured the contract we drafted; 8 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

8unverified

Licence: 0 of the 8 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from hdjang/Feature-Selective-Anchor-Free-Module-for-Single-Shot-Object-Detection. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

anchor_target hdjang/Feature-Selective-Anchor-Free-Module-for-Single-Shot-Object-Detection/mmdet/core/anchor/anchor_target.py community (archive-listed) unverified Apache-2.0 (permissive) · 94d77124832ebf0b · report
anchor_target_single hdjang/Feature-Selective-Anchor-Free-Module-for-Single-Shot-Object-Detection/mmdet/core/anchor/anchor_target.py community (archive-listed) unverified Apache-2.0 (permissive) · 73823f326d7922ae · report
calc_region hdjang/Feature-Selective-Anchor-Free-Module-for-Single-Shot-Object-Detection/mmdet/core/anchor/guided_anchor_target.py community (archive-listed) unverified Apache-2.0 (permissive) · 736c7ce8a0faa02a · report
ga_loc_target hdjang/Feature-Selective-Anchor-Free-Module-for-Single-Shot-Object-Detection/mmdet/core/anchor/guided_anchor_target.py community (archive-listed) unverified Apache-2.0 (permissive) · 2440313353f0c835 · report
ga_shape_target hdjang/Feature-Selective-Anchor-Free-Module-for-Single-Shot-Object-Detection/mmdet/core/anchor/guided_anchor_target.py community (archive-listed) unverified Apache-2.0 (permissive) · 5f757868dd1d171d · report
images_to_levels hdjang/Feature-Selective-Anchor-Free-Module-for-Single-Shot-Object-Detection/mmdet/core/anchor/anchor_target.py community (archive-listed) unverified Apache-2.0 (permissive) · 8fa249eba3a0ce57 · report
point_target hdjang/Feature-Selective-Anchor-Free-Module-for-Single-Shot-Object-Detection/mmdet/core/anchor/point_target.py community (archive-listed) unverified Apache-2.0 (permissive) · a08ee98e88ad24e7 · report
point_target_single hdjang/Feature-Selective-Anchor-Free-Module-for-Single-Shot-Object-Detection/mmdet/core/anchor/point_target.py community (archive-listed) unverified Apache-2.0 (permissive) · b660461f38b4382b · report

Tasks

Object Detectionfeature selectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection COCO minival FSAF (ResNeXt-101, anchor-based branches) AP50 62.4 #163 of 220 Archive leaderboard report
Object Detection COCO minival FSAF (ResNeXt-101, anchor-based branches) box AP 41.6 #163 of 220 Archive leaderboard report
Object Detection COCO minival FSAF (ResNet-101, anchor-based branches) AP50 59.2 #189 of 220 Archive leaderboard report
Object Detection COCO minival FSAF (ResNet-101, anchor-based branches) box AP 39.3 #189 of 220 Archive leaderboard report
Object Detection COCO minival FSAF (ResNet-101) AP50 58.0 #201 of 220 Archive leaderboard report
Object Detection COCO minival FSAF (ResNet-101) box AP 37.9 #201 of 220 Archive leaderboard report
Object Detection COCO minival FSAF (ResNet-50) AP50 55.0 #206 of 220 Archive leaderboard report
Object Detection COCO minival FSAF (ResNet-50) AP75 37.9 #206 of 220 Archive leaderboard report
Object Detection COCO minival FSAF (ResNet-50) APL 48.2 #206 of 220 Archive leaderboard report
Object Detection COCO minival FSAF (ResNet-50) APM 39.6 #206 of 220 Archive leaderboard report
Object Detection COCO minival FSAF (ResNet-50) APS 19.8 #206 of 220 Archive leaderboard report
Object Detection COCO minival FSAF (ResNet-50) box AP 35.9 #206 of 220 Archive leaderboard report
Object Detection COCO test-dev FSAF (ResNeXt-101, multi-scale) AP50 65.2 #143 of 225 Archive leaderboard report
Object Detection COCO test-dev FSAF (ResNeXt-101, multi-scale) AP75 48.6 #143 of 225 Archive leaderboard report
Object Detection COCO test-dev FSAF (ResNeXt-101, multi-scale) APL 54.6 #143 of 225 Archive leaderboard report
Object Detection COCO test-dev FSAF (ResNeXt-101, multi-scale) APM 47.1 #143 of 225 Archive leaderboard report
Object Detection COCO test-dev FSAF (ResNeXt-101, multi-scale) APS 29.7 #143 of 225 Archive leaderboard report
Object Detection COCO test-dev FSAF (ResNeXt-101, multi-scale) box mAP 44.6 #143 of 225 Archive leaderboard report
Object Detection COCO test-dev FSAF (ResNet-101, single-scale) AP50 61.5 #187 of 225 Archive leaderboard report
Object Detection COCO test-dev FSAF (ResNet-101, single-scale) AP75 44 #187 of 225 Archive leaderboard report
Object Detection COCO test-dev FSAF (ResNet-101, single-scale) APL 51.3 #187 of 225 Archive leaderboard report
Object Detection COCO test-dev FSAF (ResNet-101, single-scale) APM 44.2 #187 of 225 Archive leaderboard report
Object Detection COCO test-dev FSAF (ResNet-101, single-scale) APS 24 #187 of 225 Archive leaderboard report
Object Detection COCO test-dev FSAF (ResNet-101, single-scale) Hardware Burden 38G #187 of 225 Archive leaderboard report
Object Detection COCO test-dev FSAF (ResNet-101, single-scale) box mAP 40.9 #187 of 225 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: FSAF

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionFPNFSAFFocal LossGlobal Average PoolingGrouped ConvolutionKaiming InitializationMax PoolingNon Maximum SuppressionRandom Horizontal FlipReLUResNeXtResNeXt BlockResidual BlockResidual ConnectionRetinaNetSGD with MomentumWeight Decay

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