Methods › General › Prioritized Sampling › ATSS
Adaptive Training Sample Selection
ATSS
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Adaptive Training Sample Selection, or ATSS, is a method to automatically select positive and negative samples according to statistical characteristics of object. It bridges the gap between anchor-based and anchor-free detectors.
For each ground-truth box g on the image, we first find out its candidate positive samples. As described in Line 3 to 6, on each pyramid level, we select k anchor boxes whose center are closest to the center of g based on L2 distance. Supposing there are ℒ feature pyramid levels, the ground-truth box g will have k×ℒ candidate positive samples. After that, we compute the IoU between these candidates and the ground-truth g as 𝒟_g in Line 7, whose mean and standard deviation are computed as m_g and v_g in Line 8 and Line 9. With these statistics, the IoU threshold for this ground-truth g is obtained as t_g=m_g+v_g in Line 10. Finally, we select these candidates whose IoU are greater than or equal to the threshold t_g as final positive samples in Line 11 to 15.
Notably ATSS also limits the positive samples' center to the ground-truth box as shown in Line 12. Besides, if an anchor box is assigned to multiple ground-truth boxes, the one with the highest IoU will be selected. The rest are negative samples.
In Syntology the paper matched by title, arXiv:2604.04029, held, no code (no_code; paper_only). The lookup matched a paper by its title, arXiv:2604.04029, not a method entry. The archive credits no paper with an arXiv id for this method, so whether this answer (about arXiv:2604.04029) is about this method is not checked; it does not say whether this method has code.
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: 16 · with a code link: 13 · where Syntology ran a sample: 5 (5 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 (5 of 16 tagged: 5 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 16 of 16, 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.
-
HQOD: Harmonious Quantization for Object Detection 5 Aug 2024 · 1 repository · arXiv:2408.02561
-
Generalized Mask-aware IoU for Anchor Assignment for Real-time Instance Segmentation 28 Dec 2023 · 0 repositories · arXiv:2312.17031
-
Being Aware of Localization Accuracy By Generating Predicted-IoU-Guided Quality Scores 23 Sep 2023 · 1 repository · arXiv:2309.13269
-
How to Train an Accurate and Efficient Object Detection Model on Any Dataset 30 Nov 2022 · 1 repository · arXiv:2211.17170
-
DETRs with Collaborative Hybrid Assignments Training 22 Nov 2022 · 6 repositories · arXiv:2211.12860Syntology 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 5 harvested samples)
-
Sample hardness based gradient loss for long-tailed cervical cell detection 7 Aug 2022 · 0 repositories · arXiv:2208.03779
-
RecursiveMix: Mixed Learning with History 14 Mar 2022 · 1 repository · arXiv:2203.06844
-
Mask-aware IoU for Anchor Assignment in Real-time Instance Segmentation 19 Oct 2021 · 1 repository · arXiv:2110.09734
-
TOOD: Task-aligned One-stage Object Detection 17 Aug 2021 · 6 repositories · arXiv:2108.07755Syntology official (archive's flag): 1 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified (of 4 harvested samples) · 3 pointer-only (licence)
-
Disentangle Your Dense Object Detector 7 Jul 2021 · 2 repositories · arXiv:2107.02963
-
Control Distance IoU and Control Distance IoU Loss Function for Better Bounding Box Regression 22 Mar 2021 · 1 repository · arXiv:2103.11696
-
Implicit Feature Pyramid Network for Object Detection 25 Dec 2020 · 0 repositories · arXiv:2012.13563
-
Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection 25 Nov 2020 · 5 repositories · arXiv:2011.12885
-
RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder 29 Oct 2020 · 4 repositories · arXiv:2010.15831Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 5 harvested samples)
-
Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection 8 Jun 2020 · 7 repositories · arXiv:2006.04388Syntology community repositories only · 22 ran (of which 0 constructed an object rather than computing a result; 21 with no instrument failure: 1 honoured, 0 violated, 20 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified (of 24 harvested samples) · 2 pointer-only (licence)
-
Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection 5 Dec 2019 · 13 repositories · arXiv:1912.02424Syntology community repositories only · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples)
Tasks archive 2025-07-28
20 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