Papers › Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training
Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training
Hongkai Zhang, Hong Chang, Bingpeng Ma, Naiyan Wang, Xilin Chen
Although two-stage object detectors have continuously advanced the state-of-the-art performance in recent years, the training process itself is far from crystal. In this work, we first point out the inconsistency problem between the fixed network settings and the dynamic training procedure, which greatly affects the performance. For example, the fixed label assignment strategy and regression loss function cannot fit the distribution change of proposals and thus are harmful to training high quality detectors. Consequently, we propose Dynamic R-CNN to adjust the label assignment criteria (IoU threshold) and the shape of regression loss function (parameters of SmoothL1 Loss) automatically based on the statistics of proposals during training. This dynamic design makes better use of the training samples and pushes the detector to fit more high quality samples. Specifically, our method improves upon ResNet-50-FPN baseline with 1.9% AP and 5.5% AP₉₀ on the MS COCO dataset with no extra overhead. Codes and models are available at https://github.com/hkzhang95/DynamicRCNN.
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="2004.06002")
Code
Syntology Ran 2 of 18 code samples harvested from 2 repositories linked to this paper; 16 have no recorded run. Of those that ran: 1 ran · violated contract; 1 ran with no contract checked.
By repository: official repository: 4 samples from 1 repository, 2 ran; community (archive-listed): 14 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.
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
18 samples harvested; 2 ran; 0 honoured the contract we drafted; 16 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: 0 of the 18 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.
2531c930ac17dddf · report
e261fa29066b37e5 · report
b99b85e38568b360 · report
426fd02a2beaf826 · report
6a7ed994a87db611 · report
1dd00ccb42e850dc · report
34a7030ddea70bdd · report
a66c7009b985da0a · report
736c7ce8a0faa02a · report
8f43d2c26227a141 · report
a57ba57f6dde621b · report
2440313353f0c835 · report
e3463fa8772a18a9 · report
8fa249eba3a0ce57 · report
99bbbfc95abdc86a · report
a08ee98e88ad24e7 · report
b660461f38b4382b · report
3dc30523833b925a · report
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Object Detection | COCO test-dev | Dynamic R-CNN (ResNet-101-DCN, multi-scale) | AP50 | 68.3 | #93 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | Dynamic R-CNN (ResNet-101-DCN, multi-scale) | AP75 | 55.6 | #93 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | Dynamic R-CNN (ResNet-101-DCN, multi-scale) | APL | 61.2 | #93 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | Dynamic R-CNN (ResNet-101-DCN, multi-scale) | APM | 53.0 | #93 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | Dynamic R-CNN (ResNet-101-DCN, multi-scale) | APS | 32.8 | #93 of 225 | Archive leaderboard | report |
| Object Detection | COCO test-dev | Dynamic R-CNN (ResNet-101-DCN, multi-scale) | box mAP | 50.1 | #93 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: Dynamic R-CNN
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