</> Code with Papers by Syntology

Papers › Complete Instances Mining for Weakly Supervised Instance Segmentation

Complete Instances Mining for Weakly Supervised Instance Segmentation

12 Feb 2024International Joint Conference on Artificial Intelligence 2023 8arXiv:2402.07633archive 2025-07-28

Zecheng Li, Zening Zeng, Yuqi Liang, Jin-Gang Yu

Weakly supervised instance segmentation (WSIS) using only image-level labels is a challenging task due to the difficulty of aligning coarse annotations with the finer task. However, with the advancement of deep neural networks (DNNs), WSIS has garnered significant attention. Following a proposal-based paradigm, we encounter a redundant segmentation problem resulting from a single instance being represented by multiple proposals. For example, we feed a picture of a dog and proposals into the network and expect to output only one proposal containing a dog, but the network outputs multiple proposals. To address this problem, we propose a novel approach for WSIS that focuses on the online refinement of complete instances through the use of MaskIoU heads to predict the integrity scores of proposals and a Complete Instances Mining (CIM) strategy to explicitly model the redundant segmentation problem and generate refined pseudo labels. Our approach allows the network to become aware of multiple instances and complete instances, and we further improve its robustness through the incorporation of an Anti-noise strategy. Empirical evaluations on the PASCAL VOC 2012 and MS COCO datasets demonstrate that our method achieves state-of-the-art performance with a notable margin. Our implementation will be made available at https://github.com/ZechengLi19/CIM.

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="2402.07633")

Code

Syntology Ran 8 of 9 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 1 ran · our draft was wrong; 7 ran with no contract checked.

By repository: official repository: 9 samples from 1 repository, 8 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

ZechengLi19/CIM officialmentioned in paperpytorchMIT 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

9 samples harvested; 8 ran; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
7ran
1unverified

Licence: 0 of the 9 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 ZechengLi19/CIM. “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.

binary_mask_to_rle ZechengLi19/CIM/lib/datasets/pycococreatortools.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · d805cf01161ac845 · report
close_contour ZechengLi19/CIM/lib/datasets/pycococreatortools.py official repository ran fingerprinted MIT (permissive) · 24680b34da633bbd · report
dis_eval ZechengLi19/CIM/lib/datasets/dis_eval.py official repository ran MIT (permissive) · dd2212897360cbfa · report
filter_for_training ZechengLi19/CIM/lib/datasets/roidb.py official repository ran MIT (permissive) · 7951428fcb43dcc0 · report
pr_conv2d ZechengLi19/CIM/lib/bp/exbp.py official repository ran MIT (permissive) · 7bf64121ea2939d9 · report
pr_linear ZechengLi19/CIM/lib/bp/exbp.py official repository ran MIT (permissive) · e7f202798fa936b4 · report
rank_for_training ZechengLi19/CIM/lib/datasets/roidb.py official repository ran MIT (permissive) · 1d0f686f173313ef · report
resize_binary_mask ZechengLi19/CIM/lib/datasets/pycococreatortools.py official repository ran MIT (permissive) · 85747a26d672282d · report
parse_rec ZechengLi19/CIM/lib/datasets/dis_eval.py official repository unverified MIT (permissive) · 0eafc51289a49033 · report

Tasks

Instance SegmentationSegmentationSemantic SegmentationWeakly-supervised instance segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image-level Supervised Instance Segmentation COCO 2017 val CIM + Mask R-CNN AP 17.0 #3 of 6 Archive leaderboard report
Image-level Supervised Instance Segmentation COCO 2017 val CIM + Mask R-CNN AP@50 29.4 #3 of 6 Archive leaderboard report
Image-level Supervised Instance Segmentation COCO 2017 val CIM + Mask R-CNN AP@75 17.0 #3 of 6 Archive leaderboard report
Image-level Supervised Instance Segmentation COCO 2017 val CIM AP 11.9 #5 of 6 Archive leaderboard report
Image-level Supervised Instance Segmentation COCO 2017 val CIM AP@50 22.8 #5 of 6 Archive leaderboard report
Image-level Supervised Instance Segmentation COCO 2017 val CIM AP@75 11.1 #5 of 6 Archive leaderboard report
Image-level Supervised Instance Segmentation COCO test-dev CIM + Mask R-CNN AP 17.2 #3 of 7 Archive leaderboard report
Image-level Supervised Instance Segmentation COCO test-dev CIM + Mask R-CNN AP@50 29.7 #3 of 7 Archive leaderboard report
Image-level Supervised Instance Segmentation COCO test-dev CIM + Mask R-CNN AP@75 17.3 #3 of 7 Archive leaderboard report
Image-level Supervised Instance Segmentation COCO test-dev CIM AP 12.0 #7 of 7 Archive leaderboard report
Image-level Supervised Instance Segmentation COCO test-dev CIM AP@50 23.0 #7 of 7 Archive leaderboard report
Image-level Supervised Instance Segmentation COCO test-dev CIM AP@75 11.3 #7 of 7 Archive leaderboard report
Image-level Supervised Instance Segmentation PASCAL VOC 2012 val CIM + Mask R-CNN mAP@0.25 68.7 #3 of 13 Archive leaderboard report
Image-level Supervised Instance Segmentation PASCAL VOC 2012 val CIM + Mask R-CNN mAP@0.5 55.9 #3 of 13 Archive leaderboard report
Image-level Supervised Instance Segmentation PASCAL VOC 2012 val CIM + Mask R-CNN mAP@0.7 37.1 #3 of 13 Archive leaderboard report
Image-level Supervised Instance Segmentation PASCAL VOC 2012 val CIM + Mask R-CNN mAP@0.75 30.9 #3 of 13 Archive leaderboard report
Image-level Supervised Instance Segmentation PASCAL VOC 2012 val CIM mAP@0.25 64.9 #4 of 13 Archive leaderboard report
Image-level Supervised Instance Segmentation PASCAL VOC 2012 val CIM mAP@0.5 51.1 #4 of 13 Archive leaderboard report
Image-level Supervised Instance Segmentation PASCAL VOC 2012 val CIM mAP@0.7 32.4 #4 of 13 Archive leaderboard report
Image-level Supervised Instance Segmentation PASCAL VOC 2012 val CIM mAP@0.75 26.1 #4 of 13 Archive leaderboard report
Point-Supervised Instance Segmentation PASCAL VOC 2012 val CIM + Mask R-CNN mAP@0.25 67.8 #2 of 3 Archive leaderboard report
Point-Supervised Instance Segmentation PASCAL VOC 2012 val CIM + Mask R-CNN mAP@0.5 55.5 #2 of 3 Archive leaderboard report
Point-Supervised Instance Segmentation PASCAL VOC 2012 val CIM + Mask R-CNN mAP@0.7 36.6 #2 of 3 Archive leaderboard report
Point-Supervised Instance Segmentation PASCAL VOC 2012 val CIM + Mask R-CNN mAP@0.75 31.1 #2 of 3 Archive leaderboard report
Weakly-supervised instance segmentation PASCAL VOC 2012 val CIM + Mask R-CNN mAP@0.25 68.7 #4 of 6 Archive leaderboard report
Weakly-supervised instance segmentation PASCAL VOC 2012 val CIM + Mask R-CNN mAP@0.5 55.9 #4 of 6 Archive leaderboard report
Weakly-supervised instance segmentation PASCAL VOC 2012 val CIM + Mask R-CNN mAP@0.75 30.9 #4 of 6 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

AWARE

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