Papers › A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in...
A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detection
Kemal Oksuz, Baris Can Cam, Emre Akbas, Sinan Kalkan
We propose average Localisation-Recall-Precision (aLRP), a unified, bounded, balanced and ranking-based loss function for both classification and localisation tasks in object detection. aLRP extends the Localisation-Recall-Precision (LRP) performance metric (Oksuz et al., 2018) inspired from how Average Precision (AP) Loss extends precision to a ranking-based loss function for classification (Chen et al., 2020). aLRP has the following distinct advantages: (i) aLRP is the first ranking-based loss function for both classification and localisation tasks. (ii) Thanks to using ranking for both tasks, aLRP naturally enforces high-quality localisation for high-precision classification. (iii) aLRP provides provable balance between positives and negatives. (iv) Compared to on average ∼6 hyperparameters in the loss functions of state-of-the-art detectors, aLRP Loss has only one hyperparameter, which we did not tune in practice. On the COCO dataset, aLRP Loss improves its ranking-based predecessor, AP Loss, up to around $5$ AP points, achieves $48.9$ AP without test time augmentation and outperforms all one-stage detectors. Code available at: https://github.com/kemaloksuz/aLRPLoss .
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="2009.13592")
Code
Syntology Ran 2 of 2 code samples harvested from 2 repositories linked to this paper; 0 have no recorded run. Of those that ran: 2 ran with no contract checked.
By repository: community (archive-listed): 2 samples from 2 repositories, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.
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
2 samples harvested; 2 ran; 0 honoured the contract we drafted; 0 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.
Licence: 1 of the 2 samples is 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.
b33b07a0e7320129 · report
7628eda0d3740ba1 · report
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Object Detection | COCO minival | Faster R-CNN+aLRP Loss (ResNet-50, 500 scale) | AP50 | 60.7 | #176 of 220 | Archive leaderboard | report |
| Object Detection | COCO minival | Faster R-CNN+aLRP Loss (ResNet-50, 500 scale) | AP75 | 43.3 | #176 of 220 | Archive leaderboard | report |
| Object Detection | COCO minival | Faster R-CNN+aLRP Loss (ResNet-50, 500 scale) | box AP | 40.7 | #176 of 220 | Archive leaderboard | report |
| Object Detection | COCO minival | RetinaNet+aLRP Loss (ResNet-50, 500 scale) | AP50 | 60.3 | #183 of 220 | Archive leaderboard | report |
| Object Detection | COCO minival | RetinaNet+aLRP Loss (ResNet-50, 500 scale) | AP75 | 42.3 | #183 of 220 | Archive leaderboard | report |
| Object Detection | COCO minival | RetinaNet+aLRP Loss (ResNet-50, 500 scale) | box AP | 40.2 | #183 of 220 | Archive leaderboard | report |
| Object Detection | COCO minival | FoveaBox+aLRP Loss (ResNet-50, 500 scale) | AP50 | 58.8 | #186 of 220 | Archive leaderboard | report |
| Object Detection | COCO minival | FoveaBox+aLRP Loss (ResNet-50, 500 scale) | AP75 | 41.5 | #186 of 220 | Archive leaderboard | report |
| Object Detection | COCO minival | FoveaBox+aLRP Loss (ResNet-50, 500 scale) | box AP | 39.7 | #186 of 220 | Archive leaderboard | report |
| Object Detection | COCO test-dev | aLRP Loss (ResNext-101-64x4d, DCN, multiscale test) | AP50 | 70.3 | #90 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | aLRP Loss (ResNext-101-64x4d, DCN, multiscale test) | AP75 | 53.9 | #90 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | aLRP Loss (ResNext-101-64x4d, DCN, multiscale test) | APL | 63.0 | #90 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | aLRP Loss (ResNext-101-64x4d, DCN, multiscale test) | APM | 53.1 | #90 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | aLRP Loss (ResNext-101-64x4d, DCN, multiscale test) | APS | 32.0 | #90 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | aLRP Loss (ResNext-101-64x4d, DCN, multiscale test) | box mAP | 50.2 | #90 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | aLRP Loss (ResNext-101-64x4d, DCN, single scale) | AP50 | 69.3 | #100 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | aLRP Loss (ResNext-101-64x4d, DCN, single scale) | AP75 | 52.5 | #100 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | aLRP Loss (ResNext-101-64x4d, DCN, single scale) | APL | 62.1 | #100 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | aLRP Loss (ResNext-101-64x4d, DCN, single scale) | APM | 51.5 | #100 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | aLRP Loss (ResNext-101-64x4d, DCN, single scale) | APS | 30.8 | #100 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | aLRP Loss (ResNext-101-64x4d, DCN, single scale) | box mAP | 48.9 | #100 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | aLRP Loss (ResNext-101-64x4d, single scale) | AP50 | 68.4 | #113 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | aLRP Loss (ResNext-101-64x4d, single scale) | AP75 | 51.1 | #113 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | aLRP Loss (ResNext-101-64x4d, single scale) | APL | 59.1 | #113 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | aLRP Loss (ResNext-101-64x4d, single scale) | APM | 50.8 | #113 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | aLRP Loss (ResNext-101-64x4d, single scale) | APS | 30.2 | #113 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | aLRP Loss (ResNext-101-64x4d, single scale) | box mAP | 47.8 | #113 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | aLRP Loss (ResNext-101, DCN, 500 scale) | AP50 | 65.0 | #144 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | aLRP Loss (ResNext-101, DCN, 500 scale) | AP75 | 47.5 | #144 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | aLRP Loss (ResNext-101, DCN, 500 scale) | APL | 58.3 | #144 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | aLRP Loss (ResNext-101, DCN, 500 scale) | APM | 48.1 | #144 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | aLRP Loss (ResNext-101, DCN, 500 scale) | APS | 24.6 | #144 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | aLRP Loss (ResNext-101, DCN, 500 scale) | box mAP | 44.6 | #144 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.
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