Methods › Computer Vision › Object Detection Models › Dynamic R-CNN
Dynamic R-CNN
Introduced by Hongkai Zhang et al. in Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Dynamic R-CNN is an object detection method that adjusts the label assignment criteria (IoU threshold) and the shape of regression loss function (parameters of Smooth L1 Loss) automatically based on the statistics of proposals during training. The motivation is that in previous two-stage object detectors, there is an inconsistency problem between the fixed network settings and the dynamic training procedure. 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.
It consists of two components: Dynamic Label Assignment and Dynamic Smooth L1 Loss, which are designed for the classification and regression branches, respectively.
For Dynamic Label Assignment, we want our model to be discriminative for high IoU proposals, so we gradually adjust the IoU threshold for positive/negative samples based on the proposals distribution in the training procedure. Specifically, we set the threshold as the IoU of the proposal at a certain percentage since it can reflect the quality of the overall distribution.
For Dynamic Smooth L1 Loss, we want to change the shape of the regression loss function to adaptively fit the distribution change of error and ensure the contribution of high quality samples to training. This is achieved by adjusting the β in Smooth L1 Loss based on the error distribution of the regression loss function, in which β actually controls the magnitude of the gradient of small errors.
In Syntology harvested code stored, below machine verification (unverified_code; harvested), served level V1; retrieve with get_harvested_code_for_paper(arxiv_id='2004.06002'). Repositories: 3 listed of 3 in the graph, strongest link: official. The lookup matched a paper by its title, arXiv:2004.06002, not a method entry. This answer is about arXiv:2004.06002, the paper the archive credits with this method.
Origin paper of this answer, arXiv:2004.06002 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified (of 18 harvested samples) · 1 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.
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.
What each level means, quoted from Syntology's server card: V0 “imports”; V1 “executes against a synthesized fixture and returns a value of the recorded type”; V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” The card adds: “No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.” A level quoted in two parts is one definition the card writes as two clauses joined by a double hyphen, each clause quoted on its own (how these levels are quoted).
Papers archive 2025-07-28
archive papers tagged: 3 · with a code link: 1 · where Syntology ran a sample: 1 (1 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 (1 of 3 tagged: 1 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 3 of 3, 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.
-
Enhancing Tree Type Detection in Forest Fire Risk Assessment: Multi-Stage Approach and Color Encoding with Forest Fire Risk Evaluation Framework for UAV Imagery 27 Jul 2024 · 0 repositories · arXiv:2407.19184
-
Fracture Detection in Wrist X-ray Images Using Deep Learning-Based Object Detection Models 14 Nov 2021 · 0 repositories · arXiv:2111.07355
-
Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training 13 Apr 2020 · 3 repositories · arXiv:2004.06002Syntology official (archive's flag): 3 ran · 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified (of 18 harvested samples) · 1 pointer-only (licence)
Tasks archive 2025-07-28
10 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