Papers › Learning Modulated Loss for Rotated Object Detection

Learning Modulated Loss for Rotated Object Detection

19 Nov 2019arXiv:1911.08299archive 2025-07-28

Wen Qian, Xue Yang, Silong Peng, Yue Guo, Junchi Yan

Popular rotated detection methods usually use five parameters (coordinates of the central point, width, height, and rotation angle) to describe the rotated bounding box and l1-loss as the loss function. In this paper, we argue that the aforementioned integration can cause training instability and performance degeneration, due to the loss discontinuity resulted from the inherent periodicity of angles and the associated sudden exchange of width and height. This problem is further pronounced given the regression inconsistency among five parameters with different measurement units. We refer to the above issues as rotation sensitivity error (RSE) and propose a modulated rotation loss to dismiss the loss discontinuity. Our new loss is combined with the eight-parameter regression to further solve the problem of inconsistent parameter regression. Experiments show the state-of-art performances of our method on the public aerial image benchmark DOTA and UCAS-AOD. Its generalization abilities are also verified on ICDAR2015, HRSC2016, and FDDB. Qualitative improvements can be seen in Fig 1, and the source code will be released with the publication of the paper.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 13 code samples harvested from 1 repository linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 13 samples from 1 repository, 7 ran (7 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

Mrqianduoduo/RSDet-8P-4R mentioned on GitHubtfApache-2.0Syntology: 13 samples, 7 ran (0 instrument-failed) · 6 unverified report
kawshik8/DL-project mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Self-Supervised Learning of Pretext-Invariant Representations (arXiv:1912.01991; that paper's own run record: 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; every one of the 3 samples that ran constructed an object rather than computing a result) and A Simple Framework for Contrastive Learning of Visual Representations (arXiv:2002.05709; that paper's own run record: 115 ran (of which 33 constructed an object rather than computing a result; 89 with no instrument failure: 1 honoured, 1 violated, 87 with no contract checked; 26 where Syntology's instrument failed) · 22 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

13 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

7ran
6unverified

Licence: 0 of the 13 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 Mrqianduoduo/RSDet-8P-4R. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

Mrqianduoduo/RSDet-8P-4R community (archive-listed) 13 samples, 7 ran (0 instrument-failed) · 6 unverified
bbox_transform in 11 papers libs/box_utils/bbox_transform.py ran Apache-2.0 (permissive) · d2d339a252ba46a7 · report fixture: signature ex_rois:ndarray/2/float, gt_rois:ndarray/2/float, scale_factors:list/1/float · returned ndarray · level recorded 2026-09-24
bbox_transform_inv in 11 papers libs/box_utils/bbox_transform.py ran Apache-2.0 (permissive) · 41aa50153cd73204 · report fixture: signature boxes:EagerTensor/2/float, deltas:EagerTensor/2/float, scale_factors:list/1/float · returned EagerTensor · level recorded 2026-09-24
enum_ratios libs/box_utils/anchor_utils.py ran Apache-2.0 (permissive) · 07832d24c2b725e2 · report fixture: signature anchors:EagerTensor/2/float, anchor_ratios:list/1/float · returned tuple · level recorded 2026-09-24
enum_scales libs/box_utils/anchor_utils.py ran Apache-2.0 (permissive) · d7d04d0980025fa0 · report fixture: signature base_anchor:EagerTensor/1/float, anchor_scales:list/1/float · returned SymbolicTensor · level recorded 2026-09-24
focal_loss in 65 papers
census: 6 implementations from 13 papers, 4 distinct outputs across 3 buckets, one shared input per bucket
libs/losses/losses.py ran Apache-2.0 (permissive) · e57f95591345ae49 · report fixture: returned SymbolicTensor · level recorded 2026-09-24
focal_loss_ libs/losses/losses.py ran Apache-2.0 (permissive) · 33ffc6daf73c0d55 · report fixture: signature labels:EagerTensor/1/int, pred:EagerTensor/1/float, anchor_state:EagerTensor/1/int, alpha:float/0/float, gamma:float/0/float · returned EagerTensor · level recorded 2026-09-24
rbbox_transform_inv libs/box_utils/bbox_transform.py ran Apache-2.0 (permissive) · 33ffa5657fe69075 · report fixture: signature boxes:EagerTensor/2/float, deltas:EagerTensor/2/float, scale_factors:list/1/float · returned EagerTensor · level recorded 2026-09-24
XceptionModel libs/networks/xception.bak.py unverified Apache-2.0 (permissive) · cd5c59c480f8b497 · report
reduced_kernel_size_for_small_input libs/networks/xception.bak.py unverified Apache-2.0 (permissive) · 1d0c0051ecdfaf14 · report
relu_separable_bn_block libs/networks/xception.bak.py unverified Apache-2.0 (permissive) · 23789094dc8fdfdd · report
relu_separable_bn_block libs/networks/xception.py unverified Apache-2.0 (permissive) · 46be84834b582dd8 · report
smooth_l1_loss_rcnn libs/losses/losses.py unverified Apache-2.0 (permissive) · 9ce96a058bfde15b · report

Tasks

ObjectObject DetectionObject Detection In Aerial Imagesobject-detectionregression

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection In Aerial Images DOTA RSDet mAP 74.10% #49 of 58 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