SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.08921 · 2020

Boundary-preserving Mask R-CNN

arXiv · PDF · Open in the Atlas

Code that ran

7 of 7 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 4 failures of our instrument; 0 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2007.08921.json · badge: /api/ran/2007.08921.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
hustvl/BMaskR-CNN canonical (classifier label)
classifier basis: census
7 ran · 0 no recorded run
FunctionStatusWhere it lives
boundary_loss_func Ran
ran on a synthesized input
hustvl/BMaskR-CNN/projects/BMaskR-CNN/bmaskrcnn/mask_head.py
pointer only (licence: Apache-2.0) · get_code("dce29c2ceb3a4117")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, hustvl/BMaskR-CNN, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

convert_basic_c2_names Ran
ran; our contract draft was wrong, not the code
hustvl/BMaskR-CNN/detectron2/checkpoint/c2_model_loading.py
pointer only (licence: Apache-2.0) · get_code("e8526a516b4f9206")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, hustvl/BMaskR-CNN, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

convert_c2_detectron_names Ran
ran; our contract draft was wrong, not the code
hustvl/BMaskR-CNN/detectron2/checkpoint/c2_model_loading.py
pointer only (licence: Apache-2.0) · get_code("52810b504f0d1066")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, hustvl/BMaskR-CNN, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

dice_loss_func Ran
ran on a synthesized input
hustvl/BMaskR-CNN/projects/BMaskR-CNN/bmaskrcnn/mask_head.py
pointer only (licence: Apache-2.0) · get_code("44638936059b68e8")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, hustvl/BMaskR-CNN, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

pad_masks Ran
ran; our contract draft was wrong, not the code
hustvl/BMaskR-CNN/detectron2/layers/mask_ops.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from thinklab-sjtu/bench2drivezoo, is pointer only (licence: NOASSERTION) · get_code("406f84cf799ed34d")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, hustvl/BMaskR-CNN, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

paste_mask_in_image_old Ran
ran; our contract draft was wrong, not the code
hustvl/BMaskR-CNN/detectron2/layers/mask_ops.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from thinklab-sjtu/bench2drivezoo, is pointer only (licence: NOASSERTION) · get_code("d03592674030077f")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, hustvl/BMaskR-CNN, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

paste_masks_in_image Ran
ran on a synthesized input
hustvl/BMaskR-CNN/detectron2/layers/mask_ops.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from DIG-Beihang/ALLOW, is pointer only (licence: Apache-2.0) · get_code("5837267fa2aed31c")
How it ran

The body of this sample is withheld: Apache-2.0, as GitHub detects it on this paper's repository, hustvl/BMaskR-CNN, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 5 later) and 2 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
convert_basic_c2_names 45 other papers
12 dated earlier, 33 later
1703.06870 (2017-03)
Mask R-CNN
1804.08864 (2018-04)
Learning to See the Invisible: End-to-End Trainable Amodal Instance Segmentation
1901.08164 (2019-01)
Decoupled Greedy Learning of CNNs
and 42 more not named here
convert_c2_detectron_names 29 other papers
11 dated earlier, 18 later
1703.06870 (2017-03)
Mask R-CNN
1804.08864 (2018-04)
Learning to See the Invisible: End-to-End Trainable Amodal Instance Segmentation
1901.08164 (2019-01)
Decoupled Greedy Learning of CNNs
and 26 more not named here
pad_masks 22 other papers
7 dated earlier, 15 later
1703.06870 (2017-03)
Mask R-CNN
1804.08864 (2018-04)
Learning to See the Invisible: End-to-End Trainable Amodal Instance Segmentation
1908.07836 (2019-08)
PubLayNet: largest dataset ever for document layout analysis
and 19 more not named here
paste_mask_in_image_old 22 other papers
7 dated earlier, 15 later
1703.06870 (2017-03)
Mask R-CNN
1804.08864 (2018-04)
Learning to See the Invisible: End-to-End Trainable Amodal Instance Segmentation
1908.07836 (2019-08)
PubLayNet: largest dataset ever for document layout analysis
and 19 more not named here
paste_masks_in_image 3 other papers
1 dated earlier, 2 later
2004.08955 (2020-04)
ResNeSt: Split-Attention Networks
Xu_H2FA_R-CNN_Holistic_and_Hierarchical_Feature_Alignment_for_Cross-Domain_Weakly_CVPR_2022_paper (2022 (year only))
H 2 FA R-CNN: Holistic and Hierarchical Feature Alignment for Cross-domain Weakly Supervised Object Detection

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Tremendous efforts have been made to improve mask localization accuracy in instance segmentation. Modern instance segmentation methods relying on fully convolutional networks perform pixel-wise classification, which ignores object boundaries and shapes, leading coarse and indistinct mask prediction results and imprecise localization. To remedy these problems, we propose a conceptually simple yet effective Boundary-preserving Mask R-CNN (BMask R-CNN) to leverage object boundary information to improve mask localization accuracy. BMask R-CNN contains a boundary-preserving mask head in which object boundary and mask are mutually learned via feature fusion blocks. As a result, the predicted masks are better aligned with object boundaries. Without bells and whistles, BMask R-CNN outperforms Mask R-CNN by a considerable margin on the COCO dataset; in the Cityscapes dataset, there are more accurate boundary groundtruths available, so that BMask R-CNN obtains remarkable improvements over Mask R-CNN. Besides, it is not surprising to observe that BMask R-CNN obtains more obvious improvement when the evaluation criterion requires better localization (e.g., AP$_{75}$) as shown in Fig.1. Code and models are available at \url{https://github.com/hustvl/BMaskR-CNN}.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2007.08921")
get_code_for_paper("2007.08921")
have("2007.08921")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2007.08921.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2007.08921.svg)](https://syntology.ai/paper/2007.08921)

Connect an agent — have() is free.