Methods › Computer Vision › Object Detection Models › R-FCN
Region-based Fully Convolutional Network
R-FCN
Introduced by Jifeng Dai et al. in R-FCN: Object Detection via Region-based Fully Convolutional Networks
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Region-based Fully Convolutional Networks, or R-FCNs, are a type of region-based object detector. In contrast to previous region-based object detectors such as Fast/Faster R-CNN that apply a costly per-region subnetwork hundreds of times, R-FCN is fully convolutional with almost all computation shared on the entire image.
To achieve this, R-FCN utilises position-sensitive score maps to address a dilemma between translation-invariance in image classification and translation-variance in object detection.
In Syntology harvested code stored, below machine verification (unverified_code; harvested), served level V1; retrieve with get_harvested_code_for_paper(arxiv_id='1605.06409'). Repositories: 48 listed of 48 in the graph, strongest link: official. The lookup matched a paper by its title, arXiv:1605.06409, not a method entry. This answer is about arXiv:1605.06409, the paper the archive credits with this method.
Origin paper of this answer, arXiv:1605.06409 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified (of 11 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: 32 · with a code link: 12 · where Syntology ran a sample: 3 (2 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (3 of 32 tagged: 2 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 32 of 32, 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.
-
PatchNet -- Short-range Template Matching for Efficient Video Processing 10 Mar 2021 · 1 repository · arXiv:2103.07371
-
ABOShips -- An Inshore and Offshore Maritime Vessel Detection Dataset with Precise Annotations 11 Feb 2021 · 0 repositories · arXiv:2102.05869
-
TensorFlow with user friendly Graphical Framework for object detection API 11 Jun 2020 · 1 repository · arXiv:2006.06385
-
DFR-TSD: A Deep Learning Based Framework for Robust Traffic Sign Detection Under Challenging Weather Conditions 3 Jun 2020 · 0 repositories · arXiv:2006.02578
-
KL-Divergence-Based Region Proposal Network for Object Detection 22 May 2020 · 0 repositories · arXiv:2005.11220
-
On the safety of vulnerable road users by cyclist orientation detection using Deep Learning 25 Apr 2020 · 0 repositories · arXiv:2004.11909
-
To What Extent Does Downsampling, Compression, and Data Scarcity Impact Renal Image Analysis? 22 Sep 2019 · 0 repositories · arXiv:1909.09945
-
Detecting 11K Classes: Large Scale Object Detection without Fine-Grained Bounding Boxes 14 Aug 2019 · 0 repositories · arXiv:1908.05217
-
Multi-Task Self-Supervised Object Detection via Recycling of Bounding Box Annotations 1 Jun 2019 · 0 repositories
-
Automatic Traffic Sign Detection and Recognition Using SegU-Net and a Modified Tversky Loss Function With L1-Constraint 26 Apr 2019 · 0 repositories
-
Large-scale mammography CAD with Deformable Conv-Nets 19 Feb 2019 · 0 repositories · arXiv:1902.07323
-
A Comparison of Embedded Deep Learning Methods for Person Detection 9 Dec 2018 · 0 repositories · arXiv:1812.03451
-
Fast Object Detection in Compressed Video 27 Nov 2018 · 0 repositories · arXiv:1811.11057
-
Satellite Imagery Multiscale Rapid Detection with Windowed Networks 25 Sep 2018 · 0 repositories · arXiv:1809.09978
-
Global Weighted Average Pooling Bridges Pixel-level Localization and Image-level Classification 21 Sep 2018 · 0 repositories · arXiv:1809.08264
-
DetNet: Design Backbone for Object Detection 1 Sep 2018 · 0 repositories
-
Overhead Detection: Beyond 8-bits and RGB 7 Aug 2018 · 0 repositories · arXiv:1808.02443
-
The EuroCity Persons Dataset: A Novel Benchmark for Object Detection 18 May 2018 · 0 repositories · arXiv:1805.07193
-
Quantization Mimic: Towards Very Tiny CNN for Object Detection 6 May 2018 · 0 repositories · arXiv:1805.02152
-
Sliding Line Point Regression for Shape Robust Scene Text Detection 30 Jan 2018 · 1 repository · arXiv:1801.09969
-
R-FCN-3000 at 30fps: Decoupling Detection and Classification 5 Dec 2017 · 2 repositories · arXiv:1712.01802
-
Cascade R-CNN: Delving into High Quality Object Detection 3 Dec 2017 · 8 repositories · arXiv:1712.00726Syntology official: no sample here; runs from other or unrecorded repositories · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
An Analysis of Scale Invariance in Object Detection - SNIP 22 Nov 2017 · 0 repositories · arXiv:1711.08189
-
Light-Head R-CNN: In Defense of Two-Stage Object Detector 20 Nov 2017 · 5 repositories · arXiv:1711.07264
-
Towards Interpretable R-CNN by Unfolding Latent Structures 14 Nov 2017 · 1 repository · arXiv:1711.05226
-
On Pre-Trained Image Features and Synthetic Images for Deep Learning 29 Oct 2017 · 0 repositories · arXiv:1710.10710
-
Detecting Faces Using Region-based Fully Convolutional Networks 14 Sep 2017 · 1 repository · arXiv:1709.05256
-
CoupleNet: Coupling Global Structure with Local Parts for Object Detection 9 Aug 2017 · 3 repositories · arXiv:1708.02863
-
Soft-NMS -- Improving Object Detection With One Line of Code 14 Apr 2017 · 8 repositories · arXiv:1704.04503Syntology 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples)
-
Object Detection via Aspect Ratio and Context Aware Region-based Convolutional Networks 2 Dec 2016 · 0 repositories · arXiv:1612.00534
-
Speed/accuracy trade-offs for modern convolutional object detectors 30 Nov 2016 · 14 repositories · arXiv:1611.10012
-
R-FCN: Object Detection via Region-based Fully Convolutional Networks 20 May 2016 · 48 repositories · arXiv:1605.06409Syntology community repositories only · 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified (of 11 harvested samples) · 1 pointer-only (licence)
Tasks archive 2025-07-28
20 shown of 52 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