Papers › Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers

Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers

23 Mar 2021CVPR 2021 1arXiv:2103.12340archive 2025-07-28

Lei Ke, Yu-Wing Tai, Chi-Keung Tang

Segmenting highly-overlapping objects is challenging, because typically no distinction is made between real object contours and occlusion boundaries. Unlike previous two-stage instance segmentation methods, we model image formation as composition of two overlapping layers, and propose Bilayer Convolutional Network (BCNet), where the top GCN layer detects the occluding objects (occluder) and the bottom GCN layer infers partially occluded instance (occludee). The explicit modeling of occlusion relationship with bilayer structure naturally decouples the boundaries of both the occluding and occluded instances, and considers the interaction between them during mask regression. We validate the efficacy of bilayer decoupling on both one-stage and two-stage object detectors with different backbones and network layer choices. Despite its simplicity, extensive experiments on COCO and KINS show that our occlusion-aware BCNet achieves large and consistent performance gain especially for heavy occlusion cases. Code is available at https://github.com/lkeab/BCNet.

PaperPDFConference PDFCodeCode Syntology ran

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="2103.12340")

Code

Syntology Ran 7 of 12 code samples harvested from 1 repository linked to this paper; 5 have no recorded run. Of those that ran: 7 ran with no contract checked.

By repository: official repository: 12 samples from 1 repository, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

lkeab/BCNet officialmentioned in papermentioned on GitHubpytorchMIT 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.

Code Syntology ran Syntology

12 samples harvested; 7 ran; 0 honoured the contract we drafted; 5 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.

7ran
5unverified

Licence: 0 of the 12 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 lkeab/BCNet. “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.

batched_nms lkeab/BCNet/detectron2/layers/nms.py official repository ran MIT (permissive) · 0df9d3b583fbc6cb · report
convert_basic_c2_names lkeab/BCNet/detectron2/checkpoint/c2_model_loading.py official repository ran MIT (permissive) · e8526a516b4f9206 · report
convert_c2_detectron_names lkeab/BCNet/detectron2/checkpoint/c2_model_loading.py official repository ran MIT (permissive) · 52810b504f0d1066 · report
get_contour_interior lkeab/BCNet/detectron2/layers/boundary.py official repository ran MIT (permissive) · 37048c236eb86341 · report
get_instances_contour_interior lkeab/BCNet/detectron2/layers/boundary.py official repository ran MIT (permissive) · 9b506f9da113b9eb · report
pad_masks lkeab/BCNet/detectron2/layers/mask_ops.py official repository ran fingerprinted MIT (permissive) · 406f84cf799ed34d · report
paste_mask_in_image_old lkeab/BCNet/detectron2/layers/mask_ops.py official repository ran MIT (permissive) · d03592674030077f · report
batched_nms_rotated lkeab/BCNet/detectron2/layers/nms.py official repository unverified MIT (permissive) · 4845964b76bba6c5 · report
get_center lkeab/BCNet/detectron2/layers/boundary.py official repository unverified MIT (permissive) · dac8413f65a84dfc · report
interpolate lkeab/BCNet/detectron2/layers/misc.py official repository unverified MIT (permissive) · 2902bf4410253ff7 · report
nms_rotated lkeab/BCNet/detectron2/layers/nms.py official repository unverified MIT (permissive) · d3fa37a000ad294d · report
paste_masks_in_image lkeab/BCNet/detectron2/layers/mask_ops.py official repository unverified MIT (permissive) · f74abd7e1355f8cd · report

Tasks

Amodal Instance SegmentationBoundary DetectionInstance SegmentationObject DetectionOcclusion HandlingReal-time Instance SegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Amodal Instance Segmentation WALT BCNet AP 73.2 #2 of 2 Archive leaderboard report
Instance Segmentation COCO test-dev BCNet(ResNeXt-101 + FPN+ FCOS) mask AP 41.7 #59 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev BCNet(ResNet-101-FPN + Faster RCNN) AP50 61.5 #74 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev BCNet(ResNet-101-FPN + Faster RCNN) AP75 43.1 #74 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev BCNet(ResNet-101-FPN + Faster RCNN) APL 51.1 #74 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev BCNet(ResNet-101-FPN + Faster RCNN) APM 42.4 #74 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev BCNet(ResNet-101-FPN + Faster RCNN) APS 22.7 #74 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev BCNet(ResNet-101-FPN + Faster RCNN) mask AP 39.8 #74 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev BCNet(ResNet-101-FPN + FCOS) AP50 61.2 #78 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev BCNet(ResNet-101-FPN + FCOS) AP75 42.7 #78 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev BCNet(ResNet-101-FPN + FCOS) APL 51.0 #78 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev BCNet(ResNet-101-FPN + FCOS) APM 42.3 #78 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev BCNet(ResNet-101-FPN + FCOS) APS 22.3 #78 of 112 Archive leaderboard report
Instance Segmentation COCO test-dev BCNet(ResNet-101-FPN + FCOS) mask AP 39.6 #78 of 112 Archive leaderboard report
Instance Segmentation KINS BCNet mAP 28.87 #1 of 1 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: bilayer decoupling

GCNbilayer decoupling

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