Browse State-of-the-Art › Unseen Object Instance Segmentation

Unseen Object Instance Segmentation

8 papers with code · 2 benchmarks · 2 datasets archive 2025-07-28

Computer Vision

Instance segmentation is the task of detecting and delineating each distinct object of interest appearing in an image.

Image Credit: Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

2 leaderboard tables shown for this task, 2 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.

DatasetBest model (first row in archive order)PaperCodeSyntologyCompare
OCID (1 row) MSMFormer Mean Shift Mask Transformer for Unseen Object Instance Segmentation code — Compare
WISDOM (1 row) SD Mask R-CNN Segmenting Unknown 3D Objects from Real Depth Images using Mask... 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

2 datasets 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

Papers archive 2025-07-28

archive papers tagged: 13 · with a code link: 8 · where Syntology ran a sample: 0 (0 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: none of the 13 tagged papers has a Syntology run on record

Page 1 of 1: papers 1 to 13 of 13, 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.

  • 16 Sep 2018 4 repositories listed
    We train a variant of Mask R-CNN with domain randomization on the generated dataset to perform category-agnostic instance segmentation without any hand-labeled data and we evaluate the trained network, which we refer to…
  • 28 Jun 2023 1 repository listed
    Accurate and efficient segmentation of unknown objects in unstructured environments is essential for robotic manipulation.
  • 7 Feb 2023 1 repository listed
    By applying multi-object tracking and video object segmentation on the images collected via robot pushing, our system can generate segmentation masks of all the objects in these images in a self-supervised way.
  • 21 Nov 2022 1 repository listed
    To illustrate the effectiveness of our method, we apply MSMFormer to unseen object instance segmentation.
  • 23 Sep 2021 1 repository listed
    Instance-aware segmentation of unseen objects is essential for a robotic system in an unstructured environment.
  • 30 Jul 2020 1 repository listed
    In this work, we propose a new method for unseen object instance segmentation by learning RGB-D feature embeddings from synthetic data.
  • 16 Jul 2020 1 repository listed
    We also show that our method can segment unseen objects for robot grasping.
  • 10 Feb 2020 1 repository listed
    Segmentation of unseen industrial parts is essential for autonomous industrial systems.
  • ZISVFM: Zero-Shot Object Instance Segmentation in Indoor Robotic Environments with Vision Foundation Models
    5 Feb 2025 0 repositories listed
    Service robots operating in unstructured environments must effectively recognize and segment unknown objects to enhance their functionality.
  • Adapting Segment Anything Model for Unseen Object Instance Segmentation
    23 Sep 2024 0 repositories listed
    Unseen Object Instance Segmentation (UOIS) is crucial for autonomous robots operating in unstructured environments.
  • RISeg: Robot Interactive Object Segmentation via Body Frame-Invariant Features
    4 Mar 2024 0 repositories listed
    In order to successfully perform manipulation tasks in new environments, such as grasping, robots must be proficient in segmenting unseen objects from the background and/or other objects.
  • Unseen Object Instance Segmentation with Fully Test-time RGB-D Embeddings Adaptation
    21 Apr 2022 0 repositories listed
    Segmenting unseen objects is a crucial ability for the robot since it may encounter new environments during the operation.
  • The Best of Both Modes: Separately Leveraging RGB and Depth for Unseen Object Instance Segmentation
    30 Jul 2019 0 repositories listed
    In order to function in unstructured environments, robots need the ability to recognize unseen novel objects.

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