Browse State-of-the-Art › Weakly-supervised instance segmentation
Weakly-supervised instance segmentation
20 papers with code · 3 benchmarks · 1 dataset archive 2025-07-28
Benchmarks archive 2025-07-28
3 leaderboard tables shown for this task, 3 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| COCO test-dev (7 rows) | DiscoBox (ResNeXt-101-DCN-FPN) | DiscoBox: Weakly Supervised Instance Segmentation and Semantic... | code | — | Compare |
| PASCAL VOC 2012 val (6 rows) | BBAM | BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic... | code | — | Compare |
| COCO 2017 val (2 rows) | DiscoBox (ResNet-50) | DiscoBox: Weakly Supervised Instance Segmentation and Semantic... | code | — | Compare |
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “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. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is 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. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
1 dataset whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Papers archive 2025-07-28
archive papers tagged: 39 · with a code link: 20 · where Syntology ran a sample: 2 (2 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 (2 of 39 tagged: 2 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 39 of 39, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “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 figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. 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); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
13 May 2021 3 repositories listedWe introduce DiscoBox, a novel framework that jointly learns instance segmentation and semantic correspondence using bounding box supervision.
-
13 Apr 2021 3 repositories listedOur experiments show that the new module is more suitable for the point-based supervision.
-
2 Aug 2023 2 repositories listedSISeg achieves instance segmentation results by leveraging image masks generated by existing semantic segmentation models, and it is highly efficient as we do not require additional training for semantic segmentation or…
-
3 Dec 2020 2 repositories listedWe present a high-performance method that can achieve mask-level instance segmentation with only bounding-box annotations for training.
-
22 Jun 2024 1 repository listedGenerating reliable pseudo masks from image-level labels is challenging in the weakly supervised semantic segmentation (WSSS) task due to the lack of spatial information.
-
12 Feb 2024 1 repository listed Syntology official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified (of 9 harvested samples) · 1 pointer-only (licence)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…
-
12 Dec 2023 1 repository listedInstance segmentation is a fundamental research in computer vision, especially in autonomous driving.
-
16 Nov 2023 1 repository listedTo address this issue, we propose a novel yet effective weakly-supervised surgical instrument instance segmentation approach, named Point-based Weakly-supervised Instance Segmentation (PWISeg).
-
14 Mar 2023 1 repository listedWeakly supervised instance segmentation using only bounding box annotations has recently attracted much research attention.
-
1 Jan 2023 1 repository listedTo our knowledge, this is the first work on weakly-supervised continual learning for instance segmentation of images.
-
15 Dec 2022 1 repository listedFinally, the third component creates a large-scale pseudo-labeled instance segmentation training dataset by compositing the foreground object masks onto the original and generated background images.
-
7 Dec 2022 1 repository listedIn this paper, we present a more artful framework, LiDAR-guided Weakly Supervised Instance Segmentation (LWSIS), which leverages the off-the-shelf 3D data, i. e., Point Cloud, together with the 3D boxes, as natural weak…
-
11 Oct 2022 1 repository listedMost existing methods for weakly supervised instance segmentation focus on designing heuristic losses with priors from bounding boxes.
-
3 Oct 2021 1 repository listedTwo variants of smooth maximum approximation, i. e., α-softmax function and α-quasimax function, are exploited to conquer the numeral instability introduced by maximum function of bag prediction.
-
20 Sep 2021 1 repository listedThis semantic drift occurs confusion between background and instance in training and consequently degrades the segmentation performance.
-
16 Mar 2021 1 repository listedWeakly supervised segmentation methods using bounding box annotations focus on obtaining a pixel-level mask from each box containing an object.
-
10 Sep 2020 1 repository listedFor each proposal, this MIL framework can simultaneously compute probability distributions and category-aware semantic features, with which we can formulate a large undirected graph.
-
1 Dec 2019 1 repository listedThis paper presents a weakly supervised instance segmentation method that consumes training data with tight bounding box annotations.
-
10 Aug 2018 1 repository listedWe present a weakly supervised model that jointly performs both semantic- and instance-segmentation -- a particularly relevant problem given the substantial cost of obtaining pixel-perfect annotation for these tasks.
-
3 Apr 2018 1 repository listedMotivated by this, we first design a process to stimulate peaks to emerge from a class response map.
-
WISH: Weakly Supervised Instance Segmentation using Heterogeneous Labels1 Jan 2025 0 repositories listedInstance segmentation traditionally relies on dense pixel-level annotations, making it costly and labor-intensive.
-
BAISeg: Boundary Assisted Weakly Supervised Instance Segmentation27 May 2024 0 repositories listedHow to extract instance-level masks without instance-level supervision is the main challenge of weakly supervised instance segmentation (WSIS).
-
Boosting Box-supervised Instance Segmentation with Pseudo Depth2 Mar 2024 0 repositories listedThe realm of Weakly Supervised Instance Segmentation (WSIS) under box supervision has garnered substantial attention, showcasing remarkable advancements in recent years.
-
Quantification of cardiac capillarization in single-immunostained myocardial slices using weakly supervised instance segmentation30 Nov 2023 0 repositories listedDecreased myocardial capillary density has been reported as an important histopathological feature associated with various heart disorders.
-
ClickSeg: 3D Instance Segmentation with Click-Level Weak Annotations19 Jul 2023 0 repositories listed3D instance segmentation methods often require fully-annotated dense labels for training, which are costly to obtain.
-
Weakly-Supervised Text Instance Segmentation20 Mar 2023 0 repositories listedText segmentation is a challenging vision task with many downstream applications.
-
AsyInst: Asymmetric Affinity with DepthGrad and Color for Box-Supervised Instance Segmentation7 Dec 2022 0 repositories listedThe weakly supervised instance segmentation is a challenging task.
-
Weakly Supervised Instance Segmentation using Motion Information via Optical Flow25 Feb 2022 0 repositories listedWeakly supervised instance segmentation has gained popularity because it reduces high annotation cost of pixel-level masks required for model training.
-
4 Apr 2021 0 repositories listed Syntology 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified (of 5 harvested samples)Humans have a strong class-agnostic object segmentation ability and can outline boundaries of unknown objects precisely, which motivates us to propose a box-supervised class-agnostic object segmentation (BoxCaseg) based…
-
Weakly Supervised Instance Segmentation for Videos with Temporal Mask Consistency23 Mar 2021 0 repositories listedWeakly supervised instance segmentation reduces the cost of annotations required to train models.
-
Weakly Supervised Multi-Object Tracking and Segmentation3 Jan 2021 0 repositories listed
-
Parallel Detection-and-Segmentation Learning for Weakly Supervised Instance Segmentation1 Jan 2021 0 repositories listed
-
18 Jul 2020 0 repositories listed
-
30 Jan 2020 0 repositories listed
-
7 Oct 2019 0 repositories listed
-
1 Jun 2019 0 repositories listed
-
Weakly Supervised Instance Segmentation Using Hybrid Network12 Dec 2018 0 repositories listed
-
1 Sep 2018 0 repositories listed
-
Acquire, Augment, Segment & Enjoy: Weakly Supervised Instance Segmentation of Supermarket Products5 Jul 2018 0 repositories listed
Syntology lines on 2 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
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