Papers › Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training...

Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection

5 Dec 2019CVPR 2020 6arXiv:1912.02424archive 2025-07-28

Shifeng Zhang, Cheng Chi, Yongqiang Yao, Zhen Lei, Stan Z. Li

Object detection has been dominated by anchor-based detectors for several years. Recently, anchor-free detectors have become popular due to the proposal of FPN and Focal Loss. In this paper, we first point out that the essential difference between anchor-based and anchor-free detection is actually how to define positive and negative training samples, which leads to the performance gap between them. If they adopt the same definition of positive and negative samples during training, there is no obvious difference in the final performance, no matter regressing from a box or a point. This shows that how to select positive and negative training samples is important for current object detectors. Then, we propose an Adaptive Training Sample Selection (ATSS) to automatically select positive and negative samples according to statistical characteristics of object. It significantly improves the performance of anchor-based and anchor-free detectors and bridges the gap between them. Finally, we discuss the necessity of tiling multiple anchors per location on the image to detect objects. Extensive experiments conducted on MS COCO support our aforementioned analysis and conclusions. With the newly introduced ATSS, we improve state-of-the-art detectors by a large margin to 50.7% AP without introducing any overhead. The code is available at https://github.com/sfzhang15/ATSS

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="1912.02424")

Code

Syntology Ran 0 of 4 code samples harvested from 2 repositories linked to this paper; 4 have no recorded run.

By repository: community (archive-listed): 4 samples from 2 repositories, 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.

13 repositories listed; official and paper-mentioned ones first.

sfzhang15/ATSS officialmentioned in papermentioned on GitHubpytorchNOASSERTION report
Qengineering/NanoDet-ncnn-Jetson-Nano mentioned on GitHubBSD-3-Clause report
Qengineering/NanoDet-ncnn-Raspberry-Pi-4 mentioned on GitHubBSD-3-Clause report
RangiLyu/nanodet mentioned on GitHubpytorch report
TangShengqin/ATSS-Pytorch mentioned on GitHubpytorchApache-2.0 report
Yuxiang1995/ICDAR2021_MFD mentioned on GitHubpytorchApache-2.0 report
coolbay/VSGN mentioned on GitHubpytorch report
justimyhxu/Dense-RepPoints mentioned on GitHubpytorchApache-2.0 report
open-edge-platform/geti mentioned on GitHubpytorchApache-2.0 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

4 samples harvested; 0 ran; 0 honoured the contract we drafted; 4 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.

4unverified

Licence: 0 of the 4 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 2 repositories linked to this paper, official or community; each sample names its own and says which. “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.

images_to_levels justimyhxu/Dense-RepPoints/mmdet/core/mask/dense_reppoints_target.py community (archive-listed) unverified Apache-2.0 (permissive) · abd2ab591583348b · report
mask_to_levels justimyhxu/Dense-RepPoints/mmdet/core/mask/dense_reppoints_target.py community (archive-listed) unverified Apache-2.0 (permissive) · 9109cf95d96cd527 · report
pts2result justimyhxu/Dense-RepPoints/mmdet/models/detectors/dense_reppoints_detector.py community (archive-listed) unverified Apache-2.0 (permissive) · 7e6b0e08cb2a4608 · report
reduce_mean TangShengqin/ATSS-Pytorch/mmdet/models/anchor_heads/atss_head.py community (archive-listed) unverified Apache-2.0 (permissive) · 74bdc4124307cc00 · report

Tasks

ObjectObject Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection COCO test-dev ATSS (ResNetXt-64x4d-101+DCN,multi-scale) AP50 68.9 #86 of 225 Archive leaderboard report
Object Detection COCO test-dev ATSS (ResNetXt-64x4d-101+DCN,multi-scale) AP75 56.3 #86 of 225 Archive leaderboard report
Object Detection COCO test-dev ATSS (ResNetXt-64x4d-101+DCN,multi-scale) APL 62.4 #86 of 225 Archive leaderboard report
Object Detection COCO test-dev ATSS (ResNetXt-64x4d-101+DCN,multi-scale) APM 52.9 #86 of 225 Archive leaderboard report
Object Detection COCO test-dev ATSS (ResNetXt-64x4d-101+DCN,multi-scale) APS 33.2 #86 of 225 Archive leaderboard report
Object Detection COCO test-dev ATSS (ResNetXt-64x4d-101+DCN,multi-scale) box mAP 50.7 #86 of 225 Archive leaderboard report
Object Detection COCO-O ATSS (ResNet-50) Average mAP 16.8 #37 of 45 Archive leaderboard report
Object Detection COCO-O ATSS (ResNet-50) Effective Robustness -0.91 #37 of 45 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

1x1 ConvolutionATSSAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionFPNFocal LossGlobal Average PoolingGroup NormalizationKaiming InitializationMax PoolingNon Maximum SuppressionReLUResidual BlockResidual ConnectionRetinaNetSGD with MomentumStep DecayWeight 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