Image-level Supervised Instance Segmentation

Description from the archive 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.

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. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

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.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

9 shown of 9 papers with code (14 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations
  10 Apr 2019 8 repositories listed Syntology ran 1 of 10 samples · 9 unverified
  For generating the pseudo labels, we first identify confident seed areas of object classes from attention maps of an image classification model, and propagate them to discover the entire instance areas with accurate…
• Object Counting and Instance Segmentation with Image-level Supervision
  6 Mar 2019 2 repositories listed
  Moreover, our approach improves state-of-the-art image-level supervised instance segmentation with a relative gain of 17.
• WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition
  22 Feb 2024 1 repository listed
  Weakly supervised visual recognition using inexact supervision is a critical yet challenging learning problem.
• Beyond Semantic to Instance Segmentation: Weakly-Supervised Instance Segmentation via Semantic Knowledge Transfer and Self-Refinement
  20 Sep 2021 1 repository listed
  This semantic drift occurs confusion between background and instance in training and consequently degrades the segmentation performance.
• Leveraging Instance-, Image- and Dataset-Level Information for Weakly Supervised Instance Segmentation
  10 Sep 2020 1 repository listed
  For each proposal, this MIL framework can simultaneously compute probability distributions and category-aware semantic features, with which we can formulate a large undirected graph.
• Towards Partial Supervision for Generic Object Counting in Natural Scenes
  13 Dec 2019 1 repository listed
  Our RLC framework further reduces the annotation cost arising from large numbers of object categories in a dataset by only using lower-count supervision for a subset of categories and class-labels for the remaining ones.
• Where are the Masks: Instance Segmentation with Image-level Supervision
  2 Jul 2019 1 repository listed
  A major obstacle in instance segmentation is that existing methods often need many per-pixel labels in order to be effective.
• Cyclic Guidance for Weakly Supervised Joint Detection and Segmentation
  1 Jun 2019 1 repository listed
  In this paper, we join weakly supervised object detection and segmentation tasks with a multi-task learning scheme for the first time, which uses their respective failure patterns to complement each other's learning.
• Weakly Supervised Instance Segmentation using Class Peak Response
  3 Apr 2018 1 repository listed
  Motivated by this, we first design a process to stimulate peaks to emerge from a class response map.

Syntology lines on 1 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. Read from the graph 2026-09-24.